Add 8 new integration skills + update README (39 skills total)#25
Merged
ArchieIndian merged 14 commits intomainfrom Mar 15, 2026
Merged
Add 8 new integration skills + update README (39 skills total)#25ArchieIndian merged 14 commits intomainfrom
ArchieIndian merged 14 commits intomainfrom
Conversation
Runs 6 diagnostic checks per skill (YAML parse, required fields, path conventions, cron format, stateful coherence, schema validity). Exits 1 when FAILs are present — suitable as a post-install gate in install.sh. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Detects INJECTION, CREDENTIAL, EXFILTRATION, DRIFT, and ORPHAN issues in all installed skills. Maintains content baselines for drift detection. Cron: Mondays 9am. Exits 1 on CRITICAL findings. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
… publish Scores a skill's description against should-fire/should-not-fire prompt sets. Computes precision, recall, F1, and assigns a grade A–F. Exits 1 on grade C or lower, suitable as a pre-publish gate. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Defines and switches between curated skill subsets (loadouts). Ships 4 presets (minimal, coding, research, ops) and estimates token savings per loadout vs. all-skills-active mode. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ties Reads requires_openclaw + requires_features frontmatter fields and compares against detected (or overridden) OpenClaw version. Ships feature registry with 5 runtime capabilities and their introduction versions. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add skill-doctor: diagnose silent skill discovery failures
…ecker Add skill-compatibility-checker: detect version/feature incompatibilities
Add skill-loadout-manager: named skill profiles to prevent context bloat
Add skill-trigger-tester: validate description trigger quality
Add installed-skill-auditor: weekly post-install security audit
…erlap (#21) Detects NAME_SHADOW (CRITICAL), EXACT_DUPLICATE (CRITICAL), HIGH_OVERLAP (HIGH), and MEDIUM_OVERLAP (MEDIUM) conflicts between installed skills using Jaccard similarity on description tokens. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
…ipts (#23) Detects OS_SPECIFIC_CALL, MISSING_BINARY, BREW_ONLY, PYTHON_IMPORT, and HARDCODED_PATH issues in companion scripts. Cross-checks against os_filter: frontmatter field. No external dependencies. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds 8 new integration-focused skills to the tables: - Core: skill-trigger-tester, skill-conflict-detector, skill-portability-checker - OpenClaw-native: skill-doctor, installed-skill-auditor, skill-loadout-manager, skill-compatibility-checker, heartbeat-governor Expands security section from 3 to 5 skills (adds installed-skill-auditor, skill-doctor). Updates companion script list and total skill counts. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds 8 new research-backed integration skills targeting the hardest problems in the OpenClaw + superpowers integration layer. All skills follow the established pattern: SKILL.md + STATE_SCHEMA.yaml + companion script + example-state.yaml.
New Core Skills (3)
skill-trigger-testerskill-conflict-detectorskill-portability-checkerNew OpenClaw-Native Skills (5)
skill-doctorinstalled-skill-auditorskill-loadout-managerskill-compatibility-checkerrequires_openclaw:andrequires_features:constraints against current runtimeheartbeat-governorREADME Updates
installed-skill-auditor,skill-doctor)Individual PRs
Test plan
bash scripts/validate-skills.sh— all 39 skills validpython3 <script>.py --help— no import errorspython3 skills/core/skill-trigger-tester/test.py --description "..." --should-fire "..."— prints gradepython3 skills/core/skill-conflict-detector/detect.py --scan— no CRITICAL conflicts in this repopython3 skills/openclaw-native/skill-doctor/doctor.py --scan— all skills PASSpython3 skills/openclaw-native/skill-loadout-manager/loadout.py --list— shows preset loadouts🤖 Generated with Claude Code