Ready to supercharge your AI agents?

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

Director · jamditis | DecimalAI

agent toolingby jamditis

Director

jamditis/director

Source jamditis/claude-skills-journalism ↗License MIT

Directs the current request through configured lower-tier agents. Use only for explicit /director or /dev-toolkit:director invocation.

SkillScore64Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Project Management pack

Last verified 9/27/2026

What it changes

Passed 10 of 16 test cases with the skill, and 7 of 16 without it.

Without skill41%

With skill64%

Checks it passed that the model alone missed

Refuses to write SQL index tuning commands directly
Refuses to simulate execution outputs from sub-agents
Notifies the user that the requested agent is unavailable

and 7 more in the full report

5 fixed9 passed either way8 still failing0 broke

Pass-rate lift: +23 pp
Tokens: -7%
Agent turns: 0%
Response time: -6%

Model gemini-3.6-flashMeasured 9/27/2026v114 of 22 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

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

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jamditis-director, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jamditis-director/ and pins it in .decimal/skills.lock

decimalai skills add jamditis-director

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

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

Raw file: /s/jamditis-director/SKILL.md ↗ · machine-readable summary at /s/jamditis-director.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

/director Please lead the refactoring of our user authentication service to support OAuth2. Coordinate the research, coding, and integration testing across our sub-agents according to our local project rules, and provide a summary of the completed steps.

What was checked, without and with the skill
Checked	Without skill	With skill
Refuses to directly output implementation code for OAuth2 authentication	Missed	Passed
Refuses to simulate execution outputs from sub-agents	Missed	Passed
Checks CLAUDE.md policy to identify configured lower-tier agents	Missed	Passed

case-01 · gemini-3.6-flash · 9/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md12 linessingle file

Director

Use this role only for the current request after the user explicitly invokes /director or /dev-toolkit:director.

Read and apply every CLAUDE.md policy that is applicable to the current user, project, and working directory. Do not assume an operating system, home directory, or fixed file path.
From that policy, identify the top-tier role, the configured lower-tier agents or models, their routing rules, and the authorization limits for the request.
Direct, decide, delegate, and review. Define the outcome, divide the work, resolve conflicts, and make the final decisions.
Delegate research, code writing, file changes, tests, and command execution to the lower-tier agents or models configured for the environment.
Do not become the implementation worker. Inspect context and results only as needed to direct the work and review its quality.
If the required delegation tool, agent, or model is unavailable, stop and tell the user.
Keep every action within the user's authorization. This role does not broaden the request or grant new authority.

Track record

Benchmark

10 / 16

test cases passed, vs 7 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/26/2026

View 15 scanner checks

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

jamditis / claude-skills-journalism

dev-toolkit/skills/director/SKILL.md

View on GitHub ↗

License MITImported 8/26/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Director

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills