Index of every page on this site: llms.txt
All skills
hagaiw avatar

/flow-runner

@33ac0e9
Run it yourself

Use when a request needs named skill steps coordinated into one evidence-based result.

  • 4 files
  • 2.2 KB
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/hagaiw/skillroll/flow-runner

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈25 tokens for metadata: the name and description. ≈185 when used: this file. ≈353 more on demand in 3 files.

Description uses 1.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈100 characters, or 1.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Flow runner

Execute the user's named steps; do not merely describe a plan. For each step, request exactly this Skill action: tool_name: "Skill", with arguments {"name":"<step name>"} (for example, {"name":"summarize-change"}). The tool name is always Skill, never the step name or flow-runner. Request one step at a time and wait for its result before requesting the next. After every step has returned, preserve which step supplied each fact and combine only the evidence that was returned. If a step is missing or fails, or its artifact is absent or malformed, identify that result and stop rather than counting it as completed or inventing content.

Use the flow context for the artifact format.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 33ac0e9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 6 days ago.

Activeupdated 3 months ago

README badge

README badge for hagaiw/skillroll/flow-runner