Index of every page on this site: llms.txt
All skills
chelis-lang avatar

/phase-gate

@f7af876
Run it yourself

Use when deciding whether a Chelis phase is actually complete. Applies the repo’s completion standard, checks manual gates, examples, docs, and phase-specific acceptance criteria before any completion claim.

  • 1 file
  • 2.2 KB
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/chelis-lang/chelis/phase-gate

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈55 tokens for metadata: the name and description. ≈495 when used: this file.

Description uses 2.8% 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 ≈220 characters, or 2.8%.

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.

Phase Gate

Use this skill when a phase is claimed complete or nearly complete.

Acceptance Oracle

Before judging a phase, identify its single authoritative oracle:

  • one command
  • one named suite
  • or one documented manual validation runner

Treat all other evidence as supporting material, not the completion decision itself.

Default Gate

The gate is scripts/gate.py; do not hand-type cargo test --workspace in its place:

python3 scripts/gate.py --fast        # before every push
python3 scripts/gate.py --validation  # optional troubleshooting and extra validation
python3 scripts/gate.py --list        # the canonical command list with local/CI ownership

The workspace nextest stage is CI-owned and macOS Smoke is the authoritative workspace oracle. Completion evidence is CI green on the candidate head plus the phase's named oracle, never a local workspace run alone. A --validation run is not required per PR; the phase's acceptance oracle and manual gates remain required.

Additional Required Checks

  • verify phase-specific acceptance commands or manual runners
  • inspect ignored tests and confirm they are explicitly documented
  • verify top-level executable examples still pass chelis fmt and chelis check
  • check that docs do not overclaim behavior the repo does not ship
  • verify that the named phase oracle is reflected consistently in plan docs and current-state docs
  • On the current repo workstation, HIP manual gates should be treated as locally runnable: rocminfo exposes a gfx1100 AMD Radeon 8060S GPU and hipcc is installed. Do not excuse ignored HIP suites on the assumption that this machine is CPU-only.

Completion Rule

Do not call the phase complete if any of these remain:

  • broken default gate
  • missing or ambiguous phase oracle
  • hidden manual-only acceptance criteria not documented as such
  • false-perfect machine-facing reports
  • examples/docs whose meaning contradicts the actual implementation

Source: SKILL.md on GitHub

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 f7af876. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 months ago

README badge

README badge for chelis-lang/chelis/phase-gate