Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Oss Repo Maintainer — measured AI agent skill | DecimalAI

stijnman/oss-repo-maintainer

SkillScore73Maintained

Helps maintain open-source repos: README accuracy, version consistency, andp re-release checklists. Use when syncing docs with repo reality or user saysf ix README, prep release, repo maintenance. Triggers: fix README, preprelease , repo maintenance, sync docs.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull stijnman-oss-repo-maintainer

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-oss-repo-maintainer/SKILL.md

Raw file: /s/stijnman-oss-repo-maintainer/SKILL.md ↗ · machine-readable summary at /s/stijnman-oss-repo-maintainer.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +14% lift-6% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	306%	0%
case-05	✗→✓	▲ Improved	96%	0%
case-19	✗→✓	▲ Improved	-28%	0%
case-20	✓→✓	＝ Same ✓	-6%	0%
case-03	✓→✓	＝ Same ✓	15%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/oss-repo-maintainer/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Oss Repo Maintainer

When to Use

User says fix README or task matches this capability
User says prep release or task matches this capability
User says repo maintenance or task matches this capability
User says sync docs or task matches this capability

Workflow

Diff README skill/file lists vs git tree.
Flag stale counts, missing install paths, broken links.
Propose README and CHANGELOG edits; show diff before commit.
Run validators (tests, skill validate) if present in repo.
Suggest conventional commit message; hitl-approver before git push.

Integrations

github-repo-scout
skill-collection-bootstrapper
goal-verifier

Error Handling

| Failure | Response | |---------|----------| | Not a git repo | Limit to file review only. |

Gotchas

Never push or publish without explicit user approval.

Safety & Ethics (Publication-Ready)

This skill is designed for public distribution. Constraints:

Documentation accuracy focus; no unauthorized releases.
Git push and publish require hitl-approver.
Generic OSS workflow; no hardcoded user or org paths in instructions.

Prohibited actions

No unauthorized access, malware, or harmful automation
No silent exfiltration of data, credentials, or telemetry
No destructive system changes without hitl-approver
No publication of user PII or environment secrets in outputs

Example

Input: User request matching triggers above. Output: Structured result per workflow; local artifacts only unless user opts in.

Want to see if stijnman/oss-repo-maintainer would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.