mirror of
https://github.com/trailofbits/skills.git
synced 2026-09-14 14:28:48 +08:00
Jonathan Hefner
debfb29c8e
* Fix `allowed-tools` to use spec-compliant space-delimited strings Per the agentskills.io specification, `allowed-tools` must be a single string of space-delimited patterns, not a YAML list. Converted all 23 SKILL.md files from the `- Item` list format to the correct `"Item1 Item2"` string format. Also updated the frontmatter examples in CLAUDE.md and the workflow-skill-design skill template to match. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Fix remaining allowed-tools format in firebase-apk-scanner and workflow-skill-design docs - Convert firebase-apk-scanner from comma-separated to space-delimited - Update anti-patterns.md and tool-assignment-guide.md examples from YAML lists to space-delimited strings - Remove unnecessary quotes from SKILL.md template placeholder Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Cover commands, new SKILL.md files, and fix template placeholder Extends the previous spec-compliance fixes: * Convert command frontmatter (commands/*.md) — per Claude Code docs, command files use the same frontmatter as skills, so the same space-delimited rule applies. * Convert three SKILL.md files added since the original PR: mutation-testing, trailmark-structural, trailmark-summary. * Fix the placeholder in the workflow-skill-design template. The previous "[minimum tools needed, space-delimited]" was YAML flow-sequence syntax, which parses as a list — the opposite of what the placeholder claims. Replaced with a concrete-looking space-delimited example plus a comment. Zeroize-audit agent files still use `allowed-tools:` in YAML list form. They are intentionally excluded: per the project's own docs (workflow-skill-design references), agents declare tools with `tools:` (not `allowed-tools:`). Fixing those requires changing the field name as well as the format and is out of scope for this PR. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * zeroize-audit agents: switch allowed-tools to tools Subagents declare their tool allowlist via `tools:` (comma-separated), not `allowed-tools:` — see Claude Code's subagent docs and this repo's own designing-workflow-skills/SKILL.md:47: > Skills use `allowed-tools:` in frontmatter. Agents use `tools:` > in frontmatter. Before this change, the zeroize-audit agents declared their tool list under `allowed-tools:`, which Claude Code does not read for subagents. The field was effectively a no-op; the spawned agents had no tool restriction enforced. Renames the field on all 11 agents to `tools:` and reformats the YAML list as comma-separated to match the documented format and existing agents elsewhere in the repo (e.g. function-analyzer.md, spec-compliance-checker.md). Tool sets are unchanged. Behavior change: tools now actually constrain what each spawned agent can call. The lists are the ones the original author intended. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill-improver: convert command allowed-tools to space-delimited The two command files in plugins/skill-improver/commands/ still used the JSON flow-array format (`allowed-tools: ["..."]`), which the rest of this PR converted everywhere else. Convert them to the spec-compliant space-delimited string form for consistency. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Dan Guido <dan@trailofbits.com>
1.4 KiB
1.4 KiB
description, argument-hint, allowed-tools
| description | argument-hint | allowed-tools |
|---|---|---|
| Iteratively reviews and fixes a Claude Code skill until it meets quality standards. Triggers on 'fix my skill', 'improve skill quality', 'skill improvement loop'. | <SKILL_NAME_OR_PATH> [--max-iterations N] | Bash(${CLAUDE_PLUGIN_ROOT}/scripts/setup-skill-improver.sh:*) Task Read Edit Write Glob Grep |
Skill Improver
Step 1: Resolve Skill Path
The user provided: $ARGUMENTS
Resolution rules:
- If input ends with
/SKILL.mdand file exists, use directly - If input is a directory containing
SKILL.md, use that path - Otherwise, search for matching skills:
Glob(pattern="**/SKILL.md")
Filter results to find skills matching the user's input (by skill name or path substring).
- Multiple matches: Ask the user to choose
- No matches: Report available skills
- Single match: Proceed with that path
Store the resolved absolute path to the skill directory in RESOLVED_SKILL_PATH.
Step 2: Initialize the Loop
Run the setup script with the resolved path:
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-skill-improver.sh" "<RESOLVED_SKILL_PATH>" [--max-iterations N]
Substitute <RESOLVED_SKILL_PATH> with the actual path. Add --max-iterations N only if specified.
Step 3: Follow the Skill Methodology
Apply the skill-improver:skill-improver skill to iteratively improve the target skill. The loop continues automatically via the stop hook until completion.