OpenClaw tools: advisory, troubleshooting, and skill building for OpenClaw

version
0.3.2
GitHub stars
276

Install

/plugin install claude-claw@Claudest

Run it inside Claude Code after adding the marketplace with /plugin marketplace add gupsammy/Claudest.

Contents

Discovered from source

Skills 2

Claw Advisor

Answer OpenClaw questions, suggest optimal configuration, diagnose issues, and guide design decisions. Two backends: clawdocs CLI for documentation, openclaw CLI for live state inspection.

Backends

clawdocs (documentation — always available)

CommandUse When
clawdocs fetch "<topic>" --no-header -qTopic known, need full page content
clawdocs search "<query>" --slugs-onlyNeed to find relevant doc slugs
clawdocs get <slug> --no-header -qExact slug known (e.g., channels/telegram)
clawdocs list --prefix <section>/Need to enumerate a doc section

openclaw (live state — may not be available)

CommandUse When
openclaw statusCheck channel health, recent sessions
openclaw doctor --non-interactiveRun health checks without prompts
openclaw config get <dot.path>Read a specific config value
openclaw healthCheck gateway health

If openclaw commands fail (not installed, gateway not running), proceed with docs-only advice. Do not treat this as an error.

Workflow

Phase 1: Understand

Parse $ARGUMENTS or the user's conversational question. Classify into:

  • Focused — single topic, one doc likely sufficient ("how do I set up Telegram?")
  • Broad — cross-cutting, spans multiple doc areas ("remote access with Telegram and webhooks")
  • Troubleshooting — something is broken, need diagnostic + docs
  • Design — architectural decision, compare options and tradeoffs

If ambiguous, ask one clarifying question via AskUserQuestion. Do not over-interview — default to the most likely interpretation.

If the question involves the user's current setup, gather live state:

openclaw status 2>/dev/null
openclaw doctor --non-interactive 2>/dev/null

Load topic routing to identify relevant doc sections:

@${CLAUDE_PLUGIN_ROOT}/skills/claw-advisor/references/topic-routing.md

Proceed when the question is classified and live state (if relevant) is gathered.

Phase 2: Research (Divergent)

Focused — single fetch, possibly one follow-up:

clawdocs fetch "<topic>" --no-header -q

If the result doesn't fully answer the question, search for adjacent docs:

clawdocs search "<refined query>" --slugs-only

Then fetch the best 1-2 additional slugs via clawdocs get.

Broad — identify 2-4 relevant topic areas from topic-routing.md. Spawn parallel subagents, one per area:

Task(subagent_type="general-purpose", prompt="Run `clawdocs fetch <topic> --no-header -q` via Bash and summarize: key config options, requirements, gotchas, and exact CLI commands for: <specific aspect>")

Run up to 4 subagents in parallel. Each returns a focused summary. Reconvene results in Phase 3.

Troubleshooting — always consult three sources:

  1. Domain-specific doc: clawdocs fetch "<domain>" --no-header -q
  2. Domain troubleshooting: clawdocs get "<domain>/troubleshooting" --no-header -q
  3. General troubleshooting: clawdocs get "help/troubleshooting" --no-header -q

Cross-reference with openclaw doctor --non-interactive output if available. If doctor reports fixable issues, surface the exact fix command (openclaw doctor --fix).

Design — for each option, fetch the primary doc page and any comparison or overview page (e.g., providers/index). Identify: requirements, limitations, and config complexity. Stop when each option has enough data to compare on the same dimensions.

If official docs don't cover the issue, use WebSearch for community solutions or GitHub issues as a fallback.

Proceed when all relevant docs are fetched and summarized.

Phase 3: Synthesize (Convergent)

Combine all research into a structured response:

  1. Direct answer — answer the question concisely first
  2. Configuration — exact config keys (full dot-paths for openclaw config get/set), values, and CLI commands. Use code blocks.
  3. Context — why this configuration is recommended, what tradeoffs exist
  4. Gotchas — known issues, common mistakes, prerequisites surfaced by the docs
  5. Sources — list doc slugs consulted so the user can dive deeper: clawdocs get <slug>

If docs and live state conflict, note the discrepancy and recommend openclaw <cmd> --help as ground truth.

Skill is complete when the structured response is delivered.

Constraints

  • Never invent OpenClaw flags, config keys, or API endpoints — only cite fetched documentation
  • Use --no-header -q on all clawdocs calls to suppress chrome and stderr diagnostics
  • Extract relevant sections from long doc pages — full pages waste context tokens and bury the answer
  • Limit parallel subagents to 4 — more agents add latency without proportional information gain
  • When citing configuration, include the full dot-path usable with openclaw config get/set
  • If a question is outside OpenClaw's domain entirely, say so — hallucinating outside the knowledge base erodes trust in all answers

OpenClaw Skill & Command Generator

Generate well-structured OpenClaw skills or slash commands. Both are SKILL.md files with YAML frontmatter — they share the same structure but differ in how they're triggered and described. OpenClaw uses the AgentSkills spec (pi-coding-agent) with its own frontmatter fields, tool names, and path conventions distinct from Claude Code.

Phase 0: Fetch Current Documentation

Before generating, retrieve the latest OpenClaw skill documentation:

clawdocs get "tools/skills" --no-header -q

Capture any frontmatter fields or options not already listed in {baseDir}/references/frontmatter-options.md. If clawdocs is unavailable, proceed with current references — they are sufficient. If new fields appear, use them and note the update.

Phase 1: Understand Requirements

Parse $ARGUMENTS for type hint. Users are often unclear on OpenClaw-specific conventions. Interview to gather:

  1. Primary objective — What should this skill do?
  2. Trigger scenarios — When should it activate? What exact phrases would a user say?
  3. Inputs/outputs — What does it receive and produce?
  4. Complexity — Simple, standard, or complex workflow?
  5. Gating needs — Does it require specific binaries, env vars, or config keys? (drives metadata.openclaw.requires.*)
  6. Execution needs — Sub-agent delegation via sessions_spawn? Command dispatch (bypass model)?

Proceed to Phase 2 when at minimum Objective and Trigger Scenarios are established.

Port Mode

When the user provides an existing Claude Code skill to port (file path or pasted content), skip the interview and apply this translation sequence:

  1. Read the source skill and all its supporting files (scripts, references, examples)
  2. Frontmatter — Remove invalid fields (model, context, agent, allowed-tools, hooks, license). Add metadata with requires if scripts need specific binaries. See {baseDir}/references/frontmatter-options.md for valid fields.
  3. Tool names — Apply the translation table from {baseDir}/references/claw-patterns.md: Bash→exec, Read→read, Write→write, Edit→edit, Glob/Grep→exec+find/rg, WebSearch→web_search, WebFetch→web_fetch, Task→sessions_spawn, AskUserQuestion→conversational asking
  4. Paths — Replace $CLAUDE_PLUGIN_ROOT with {baseDir}. Remove @file injection and bang-backtick references.
  5. Scripts/references — Copy as-is if they are platform-neutral Python with no Claude Code SDK dependencies. Update any internal tool name references.
  6. Proceed directly to Phase 2 Step 7 (Validate) with translated content, then Phase 3 (Deliver).

Phase 2: Generate

Apply throughout generation: use imperative voice and terse phrasing because every token in a generated skill body costs budget on every invocation. Prefer instruction over example — state the rule with its reasoning so it generalizes to every input.

Initialize directory first (when creating a new skill directory, not editing an existing file):

python3 {baseDir}/scripts/init_claw_skill.py <name> --path <dir> [--resources scripts,references,assets]

Exit 0 = directory scaffolded, proceed to Step 1. Exit 1 = naming collision; ask user whether to overwrite or rename.

Step 1 — Choose type

  • Skills: Trigger-rich, third-person description ("This skill should be used when..."); auto-triggered by routing
  • Commands: Concise, verb-first description, under 60 chars; user-invoked via / menu
  • Dispatch commands: command-dispatch: tool with command-tool — bypasses model entirely, routes directly to a named tool (rare; for pure pass-through cases)

Step 2 — Write frontmatter

Read {baseDir}/references/frontmatter-options.md for the full OpenClaw field catalog, description patterns, and the metadata single-line JSON constraint.

Key constraint: metadata must be a single-line JSON object on one line. Multi-line YAML mappings under metadata are not valid in OpenClaw.

Description density rules: Keep descriptions under ~400 characters / ~100 tokens (600 chars / 150 tokens absolute max) — they load every session. Per the OpenClaw cost formula, each skill costs 195 + 97 + field lengths characters in the system prompt; a 10-skill install with verbose descriptions burns significant context on routing metadata alone. Derive trigger phrases from the user's actual words in Phase 1, not paraphrases. See the token budget and trigger derivation principles in {baseDir}/references/frontmatter-options.md.

Intensional over extensional — state the rule with its reasoning rather than listing examples that imply the rule. An intensional rule generalizes to every input the skill will encounter; an extensional list only covers the shapes shown.

Step 3 — Validate description discoverability

Before writing the body, verify the description will route correctly. Mentally generate:

  1. 3 should-trigger prompts — realistic user messages that should activate this skill. Include at least one naive phrasing from a user who has never heard of the skill.
  2. 3 should-NOT-trigger prompts — messages in adjacent domains that are close but should not activate. These test whether the description is too broad.

Evaluate: does the description cover all should-trigger prompts? Would it plausibly reject the should-NOT-trigger prompts? If coverage is weak, revise the description — add missing trigger phrases, tighten language to exclude adjacent domains, or add a negative trigger ("Not for X").

This step catches routing misses before the rest of the skill is built. Proceed when description coverage is adequate.

Step 4 — Write body

Construction rules:

  • State objective explicitly in first sentence
  • Use imperative voice ("Analyze", "Generate", "Identify") — no first-person ("I will", "I am")
  • Context only when necessary for understanding
  • XML tags only for complex structured data
  • No "When to Use This Skill" section — body loads only after triggering; routing guidance there is never read by the routing decision
  • Avoid headers deeper than H3 — deep nesting signals content that belongs in references/, not SKILL.md
  • {baseDir} is the path variable for skill-relative file references (substituted before model sees the skill body)

Both skills and commands follow the same body pattern:

# Name

Brief overview (1-2 sentences).

## Process
1. Step one (imperative voice)
2. Step two
3. Step three

Dynamic Content:

SyntaxPurpose
$ARGUMENTSAll arguments as string
$1, $2, $3Positional arguments
{baseDir}Absolute path to skill directory (substituted at load time)

Note: @file injection and bang-backtick command expansion are Claude Code features specific to Claude Code's skill loader implementation — the pi-coding-agent skill loader only supports {baseDir} path substitution and does not implement these extensions. Do not use them in generated OpenClaw skills.

Step 5 — Script opportunity scan

Read {baseDir}/references/script-patterns.md and apply the five signal patterns to every workflow step in the skill being generated:

SignalQuestionIf yes →
Repeated GenerationDoes any step produce the same structure with different params across invocations?Parameterized script in scripts/
Unclear Tool ChoiceDoes any step combine multiple operations in a fragile sequence naturally expressible as one function?Script the procedure
Rigid ContractCan you write --help text for this step right now without ambiguity?CLI candidate
Dual-Use PotentialWould a user want to run this step from the terminal, outside the skill workflow?Design as proper CLI from the start
Consistency CriticalMust this step produce bit-for-bit identical output for identical inputs?Script — never LLM generation

For each identified script candidate:

  1. Choose the archetype from {baseDir}/references/script-patterns.md (init/validate/transform/package/query)
  2. Scaffold the script in scripts/ using the Python template from {baseDir}/references/script-patterns.md
  3. Wire it into SKILL.md with: trigger condition, exact invocation using exec tool, output interpretation

Wiring rule: A script reference must state when to invoke (trigger condition), how to invoke (exact command with flags), and what to do with the result (exit code handling, which output fields matter).

Scripts are invoked via the exec tool (not Bash). Reference paths using {baseDir}/scripts/script.py.

Step 6 — Check delegation

Read {baseDir}/references/claw-patterns.md for delegation patterns, sessions_spawn usage, cross-skill reference conventions, and tool group translations (Claude Code → OpenClaw tool name mapping).

Scan for existing resources before finalizing:

Review available OpenClaw skills (check ~/.openclaw/skills/ and workspace/skills/)
For each workflow step, ask: "Do we already have this?"

Common delegation patterns:

  • To invoke another OpenClaw skill: tell the model to read {baseDir}/../<other-skill>/SKILL.md via the read tool, or instruct the user to type /<other-skill-name>
  • For background delegation: use sessions_spawn (non-blocking; result announced back to chat)
  • Documentation lookups: exec: clawdocs get "<slug>" --no-header -q

There is no Skill tool in OpenClaw — skills are invoked by the routing model, not programmatically from within another skill.

Step 7 — Validate

When generating a new skill directory (not editing an existing single file):

python3 {baseDir}/scripts/validate_claw_skill.py <skill-directory> --output json

Exit 0 = proceed to Phase 3. Exit 1 = parse the errors array; each entry has field, message, severity. Resolve all critical and major items before writing to disk.

Explain Your Choices

When presenting the generated skill/command to the user, briefly explain:

  • What you set and why — "Added metadata.openclaw.requires.bins: [jq] because the skill calls jq in a subprocess"
  • What you excluded and why — "Left user-invocable at default (true), command-dispatch omitted (skill routes through model)"
  • Add more trigger phrases if routing misses expected inputs

Phase 3: Deliver

Output Paths

TypeLocationWhen active
Workspace skill<workspace>/skills/<name>/Next session in that workspace
Managed skill~/.openclaw/skills/<name>/Shared across all agents on this machine

Skills are session-snapshotted — changes take effect on the next new session, not the current one.

Write and Confirm

Before writing:

Writing to: [path]
This will [create new / overwrite existing] file.
Proceed?

After Creation

Summarize what was created:

  • Name and type
  • Path and when it takes effect
  • How to invoke/trigger
  • Suggested test scenario

Publish to ClawHub

Invoke only when the user explicitly requests distribution:

clawhub publish <skill-directory> --slug <slug> --version X.Y.Z --tags latest

Exit 0 = published. Exit 1 = validation or auth failure; read stdout for details.

Phase 4: Evaluate

Score the generated skill/command:

DimensionCriteria
Clarity (0-10)Instructions unambiguous, objective clear
Precision (0-10)Appropriate specificity without over-constraint
Efficiency (0-10)Token economy — maximum value per token
Completeness (0-10)Covers requirements without gaps or excess
Usability (0-10)Practical, actionable, appropriate for target use

Target: 9.0/10.0. If below, refine once addressing the weakest dimension, then deliver.

Re-run validate_claw_skill.py after any revisions and verify the validation checklist below before finalizing.

Degrees of Freedom

LevelWhen to UseFormat
High freedomMultiple valid approaches, context-dependent decisionsText instructions, heuristics
Medium freedomPreferred pattern exists, some variation acceptablePseudocode, scripts with parameters
Low freedomFragile operations, consistency critical, specific sequence requiredExact scripts, few parameters

Quality Standards

Format Economy:

  • Simple task → direct instruction, no sections
  • Moderate task → light organization with headers
  • Complex task → full semantic structure

Remove ruthlessly: Filler phrases, obvious implications, redundant framing, excessive politeness

Validation Checklist

Before finalizing an OpenClaw skill or command:

Structure:

  • SKILL.md exists with valid YAML frontmatter
  • Frontmatter has name and description fields
  • metadata field (if present) is single-line JSON on one line
  • Markdown body is present and substantial
  • Referenced files actually exist

Description Quality:

  • Uses third person ("This skill should be used when...")
  • Includes specific trigger phrases users would say (verbatim)
  • Trigger phrases derived from user's actual words, not formalized paraphrases
  • Under ~400 chars (~100 tokens); 600 chars (~150 tokens) absolute max
  • Negative triggers present if adjacent skills could false-trigger
  • Lists concrete scenarios ("create X", "configure Y")
  • Not vague or generic

OpenClaw Correctness:

  • No Claude Code-only fields: no model, context, agent, allowed-tools, hooks, license
  • No Claude Code tool names referenced in body: no Bash, WebSearch, WebFetch, Read, Write, Edit, Glob, Grep, Task, Skill, AskUserQuestion, EnterPlanMode, ExitPlanMode
  • Uses OpenClaw tool names: exec, read, write, edit, web_search, web_fetch, sessions_spawn
  • Uses {baseDir} for skill-relative paths (not $CLAUDE_PLUGIN_ROOT)
  • Output path is OpenClaw workspace (<workspace>/skills/) or managed (~/.openclaw/skills/)

Content Quality:

  • Body uses imperative/infinitive form, not second person
  • Body is focused and lean (1,500–2,000 words ideal, <5k max)
  • Detailed content moved to references/
  • Scripts are executable and documented
  • Script opportunities identified via five signal patterns
  • Script references in SKILL.md include trigger condition, invocation (exec), output handling
  • Consistency-critical steps are scripted, not left to LLM re-generation

Progressive Disclosure:

  • Core concepts in SKILL.md
  • Detailed docs in references/
  • Utilities in scripts/
  • SKILL.md references these resources
  • examples/ present if skill produces user-adaptable output (see {baseDir}/examples/sample-command/SKILL.md for a minimal command example)

Error Handling

IssueAction
Unclear requirementsAsk clarifying questions before generating
Missing contextRequest usage examples or target scenarios from user
Path issuesVerify target directory exists; let init_claw_skill.py create it
Type unclearDefault to skill (auto-triggered) if user hasn't specified
clawdocs unavailableProceed with current references — they are sufficient

Execute phases sequentially. Always fetch current documentation first.

Sponsors

Details

Marketplace
gupsammy/Claudest
Source
plugins/claude-claw
Category
Community

More from gupsammy/Claudest

All 8