pdca-fast-track
Skill605 starsChanged 3 months agoApache-2.0View on GitHub
Daniel-mode fast-track auto-approves Checkpoint 1-8 when Trust ≥ 80, fastTrack on, Design doc exists. Else L2 + manual gates. Triggers: pdca fast-track, skip checkpoints, auto approve
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ww-w-ai/bkit-claude-codeword for word, first seen Aug 14, 2026
Other versions1 project uses a version of this.
Word for word · 1
- ww-w-ai/bkit-claude-code★ 605100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- auditSkill
- bkend-authSkill
- bkend-cookbookSkill
- bkend-dataSkill
- bkend-quickstartSkill
- bkend-storageSkill
- bkit-evalsSkill
- bkit-exploreSkill
- bkit-rulesSkill
- bkitSkill
- bkit-templatesSkill
- btwSkill
- cc-version-analysisSkill
- claude-code-learningSkill
- code-reviewSkill
- controlSkill
- deploySkill
- desktop-appSkill
- development-pipelineSkill
- dynamicSkill
- enterpriseSkill
- mobile-appSkill
- pdca-batchSkill
- pdcaSkill
- pdca-watchSkill
- phase-1-schemaSkill
- phase-2-conventionSkill
- phase-3-mockupSkill
- phase-4-apiSkill
- phase-5-design-systemSkill
- phase-6-ui-integrationSkill
- phase-7-seo-securitySkill
- phase-8-reviewSkill
- phase-9-deploymentSkill
- plan-plusSkill
- pm-discoverySkill
- qa-phaseSkill
- rollbackSkill
- skill-createSkill
- skill-statusSkill
- sprintSkill
- starterSkill
- zero-script-qaSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
When any block, surface the reason with a remedy hint:
- Very specific: line 74
If a Checkpoint surfaces NO "Recommended" option, call recordCheckpoint({ decision: 'fallback', reason: 'no_recommended' }) and pause to …
- Very specific: line 80
All file IO is rooted at process.env.CLAUDE_PROJECT_DIR (or repo root).
≈ “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.
Files
PDCA Fast Track — Daniel's Track
v2.1.11 Sprint β FR-β5. Wraps
lib/control/fast-track.js. Provides a single auto-escalation gate for users who have already earned Trust ≥ 80 and produced a Design doc — Checkpoints 1-8 default to Recommended without prompting. Falls back to L2 + manual review the moment any preconditions fails (E-β5-01 / E-β5-02).
Arguments
| Argument | Description | Example |
<feature> | Feature name to engage fast-track for | /pdca-fast-track bkit-v2111-integrated-enhancement |
Behavior
Preconditions (all must pass; fail-open)
- Config enabled —
bkit.config.json#control.fastTrack.enabled === true - Trust Score ≥ 80 —
.bkit/state/trust-profile.json#trustScore≥fastTrack.minTrustScore(default 80) - Design doc exists — resolved via
bkit.config.json#pdca.docPaths.designtemplates against<feature>
When any block, surface the reason with a remedy hint:
| Block | Remedy hint |
disabled_in_config | "Set control.fastTrack.enabled = true in bkit.config.json" |
trust_score_too_low | "Run a few /pdca check cycles to raise trust" |
design_doc_missing | "Run /pdca design <feature> first" |
On engage (all preconditions pass)
- Recommend Automation Level escalation L2 →
fastTrack.autoLevel(defaultL3). - Persist engagement record to
.bkit/runtime/fast-track-log.json:{ "engaged": true, "feature": "<feature>", "engagedAt": "<ISO>", "trustScore": 85, "autoLevel": "L3", "fallbackLevel": "L2", "skipCheckpoints": [1,2,3,4,5,6,7,8], "designPath": "docs/02-design/features/<feature>.design.md", "decisions": [] } - Each Checkpoint 1-8 invocation calls
fast-track.recordCheckpointto append a decision entry (audit trail). - If a Checkpoint surfaces NO "Recommended" option, call
recordCheckpoint({ decision: 'fallback', reason: 'no_recommended' })and pause tofallbackLevel.
Security
- All file IO is rooted at
process.env.CLAUDE_PROJECT_DIR(or repo root). - Audit log JSON is OWASP A08-clean: no user-controlled keys; only
whitelisted
checkpoint(number),decision(enum),reason(sanitized string). - Design doc patterns are read from
bkit.config.json— no traversal via untrustedfeaturearg (pattern is{feature}placeholder only). - Trust score read is fail-safe: missing file returns 0 (blocks engage).
Module Dependencies
| Module | Function | Usage |
lib/control/fast-track.js | evaluatePreconditions(feature) | Block list |
lib/control/fast-track.js | engage(feature) | Audit + record |
lib/control/fast-track.js | recordCheckpoint({...}) | Per-CP decision |
lib/control/fast-track.js | isCheckpointSkipped(n) | Should we skip? |
Examples
# Engage on a Design-complete feature
/pdca-fast-track bkit-v2111-integrated-enhancement
# Result if Trust < 80
# Block: trust_score_too_low (current 68 < required 80)
# Result if Design missing
# Block: design_doc_missing → run /pdca design firstRelated
/control trust— current Trust Score breakdown/control level <0-4>— manual override/pdca-watch— observe progress while fast-tracking/pdca design <feature>— required prerequisite
ARGUMENTS:
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
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.

