agentleFS
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/apply-stage-gate/SKILL.md

apply-stage-gate

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Apply explicit GO / HOLD / RECYCLE / KILL (or supplied) stage-gate criteria with evidence thresholds and next-step conditions.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No GO is emitted while any hard criterion is unknown.

    line 27
  2. Distinctive:

    Do not turn an absent measurement into a pass.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

apply-stage-gate

Purpose

Apply explicit GO / HOLD / RECYCLE / KILL gates to a candidate or work package, tying each outcome to evidence thresholds and a next action.

Input contract

required: [candidate_record, gate_criteria, evidence_register]
optional: [prior_gate_decision, remediation_options]
constraints: [each criterion has an observable status; gate outcome and next action are explicit]

Procedure

  1. Normalize the candidate, gate criteria, evidence, and unresolved assumptions into a gate table.
  2. Evaluate every criterion as met, unmet, or unknown, preserving the cited evidence and threshold direction.
  3. Apply precedence: KILL for disqualifying hard failure, RECYCLE for repairable failure, HOLD for insufficient evidence, otherwise GO.
  4. Emit the gate decision, failed criteria, evidence gaps, and the smallest justified next action.

Output contract

produces: [gate_table, gate_decision, failed_criteria, next_action]
delta_fields: [findings, evidence_updates, uncertainties, decisions, recommended_jumps]

Quality gates

  • A-class gate: declared universe = all candidate criteria and evidence items; numerator = criteria with explicit status and source; batch increment = one evaluated criterion; stopping reason = every criterion resolved or a hard failure terminates the gate; source references = criterion/evidence IDs; direction/threshold reason = GO requires all hard criteria met, while HOLD/RECYCLE/KILL follows the declared precedence.
  • No GO is emitted while any hard criterion is unknown.

Failure and counterexamples

Do not turn an absent measurement into a pass. A repairable shortfall is RECYCLE only when a concrete remediation and re-gate condition are recorded.

Provenance map

  • concept: convergence/feasibility-assessment/stage-gate [strategy/tactic]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.