Ready to supercharge your AI agents?

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

Context — measured AI agent skill | DecimalAI

majiayu000/context

NewSkillScoreMaintained

To maintain the integrity of audit logs, we must ensure that agents use their real identities in worklogs, rather than blindly copying "codex" from templates.

by majiayu000

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

Automatic

Doc Ops pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/majiayu000-context/SKILL.md

decimalai skills pull majiayu000-context --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-context/SKILL.md https://app.decimal.ai/s/majiayu000-context/SKILL.md

Raw file: /s/majiayu000-context/SKILL.md ↗ · machine-readable summary at /s/majiayu000-context.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 4h ago

—-40% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-60%	0%
case-01	✗→✓	▲ Improved	-15%	0%
case-02	✗→✓	▲ Improved	-33%	0%
case-05	✗→✓	▲ Improved	-58%	0%
case-06	✗→✓	▲ Improved	-45%	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 — 8/3/2026

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

majiayu000 / claude-skill-registry

skills/agent/0000-dorgonman-kano-agent-backlog-s-59370436/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Context

To maintain the integrity of audit logs, we must ensure that agents use their real identities in worklogs, rather than blindly copying "codex" from templates.

Goal

Update the skill documentation and templates to explicitly require agents to use their real identity.

Non-Goals

Technical enforcement in the script code (documentation only for now).

Approach

Update SKILL.md Non-negotiables.
Update templates.md with placeholders.
Update conventions.md.

Acceptance Criteria

] SKILL.md contains the rule.
] templates.md no longer has hardcoded codex.
] conventions.md warns about identity usage.

Risks / Dependencies

Agents might ignore the docs; scripts should eventually enforce this (via --agent arg).

Worklog

2026-01-04 23:31 agent=antigravity] Created from template. 2026-01-04 23:33 agent=antigravity] State -> Done.

Want to see if majiayu000/context 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.