Ready to supercharge your AI agents?

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

Dispatch ctx work · stevesolun | DecimalAI

agent toolingby stevesolun

Dispatch ctx work

stevesolun/ctx-dispatch

Source stevesolun/ctx ↗License MIT

Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes; compute-heavy checks; or repetitive changes suited to scripts or codemods.

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 8/18/2026

What it changes

Passed 18 of 20 test cases with the skill, and 15 of 20 without it.

Without skill74%

With skill91%

Checks it passed that the model alone missed

Executes simple docstring edits locally without spawning subagents
Inspects system resources before sizing concurrency for database re-indexing
Merges evidence at the coordinator level before reporting overall completion

and 2 more in the full report

4 fixed17 passed either way2 still failing0 broke

Pass-rate lift: +17 pp
Tokens: -28%
Agent turns: 0%
Response time: -38%

Model gemini-3.6-flashMeasured 8/18/2026v121 of 23 cases passed with skill · 20 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/stevesolun-ctx-dispatch/SKILL.md https://app.decimal.ai/s/stevesolun-ctx-dispatch/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stevesolun-ctx-dispatch, 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/stevesolun-ctx-dispatch/ and pins it in .decimal/skills.lock

decimalai skills add stevesolun-ctx-dispatch

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

curl -fsSL --create-dirs -o .claude/skills/stevesolun-ctx-dispatch/SKILL.md https://app.decimal.ai/s/stevesolun-ctx-dispatch/SKILL.md

Raw file: /s/stevesolun-ctx-dispatch/SKILL.md ↗ · machine-readable summary at /s/stevesolun-ctx-dispatch.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Three parallel subagents are updating microservice repositories: Service A, Service B, and Service C. Subagent A wants write access to Service B's repository files to update a shared contract. How should file permissions/ownership be allocated?

What was checked, without and with the skill
Checked	Without skill	With skill
Enforces disjoint file ownership ensuring Subagent A only modifies Service A repository files	Missed	Passed

case-23 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md13 linessingle file

Dispatch ctx work

Identify the requested outcome, dependencies, and independently executable lanes. Keep simple work local.
Reserve subagents for bounded semantic work that benefits from isolated context.
Run lanes concurrently only when this reduces elapsed time without duplicate work or competing writes. Give each writer disjoint ownership; keep shared files with one owner.
Inspect CPU, memory, and disk pressure only before genuinely compute-heavy work, then size concurrency to the available capacity.
Keep scope, dependency resolution, and synthesis with one coordinator. Merge evidence from every required lane before reporting completion.

Track record

Benchmark

18 / 20

test cases passed, vs 15 / 20 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 v4 — 8/3/2026

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

stevesolun / ctx

.claude/skills/ctx-dispatch/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

hashgraph-online/orchestrate-engineeringCoordinate complex engineering work across bounded subagents while protecting the main context, preventing edit conflicts, and measuring whether delegation was worthwhile. Use when the user asks to delegate, parallelize, orchestrate, use subagents, fan out a review, or handle a large task with independent workstreams; do not use for small, tightly coupled, or inherently sequential tasks.Close match+13 pp pass-rate lift

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

Dispatch ctx work

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills