/pdca-fast-track
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
$ npx -y skills add popup-studio-ai/bkit-claude-code --skill pdca-fast-track --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/pdca-fast-track
Context preview
The summary Claude sees to decide when to auto-load this skill.
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
SKILL.md
pdca-fast-track.SKILL.mdname: pdca-fast-track
classification: workflow
classification-reason: PDCA flow modifier — bypasses Checkpoint 1-8 user gates
deprecation-risk: none
effort: low
description: |
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
argument-hint: "<feature>"
user-invocable: true
allowed-tools:
- Read
- Write
- Glob
imports: []
next-skill: null
pdca-phase: null
task-template: "[Fast-Track] {feature}"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)
1. **Config enabled** — `bkit.config.json#control.fastTrack.enabled === true` 2. **Trust Score ≥ 80** — `.bkit/state/trust-profile.json#trustScore` ≥ `fastTrack.minTrustScore` (default 80) 3. **Design doc exists** — resolved via `bkit.config.json#pdca.docPaths.design` templates 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)
1. Recommend Automation Level escalation L2 → `fastTrack.autoLevel` (default `L3`). 2. 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": []
}3. Each Checkpoint 1-8 invocation calls `fast-track.recordCheckpoint` to append a decision entry (audit trail). 4. If a Checkpoint surfaces NO "Recommended" option, call `recordCheckpoint({ decision: 'fallback', reason: 'no_recommended' })` and pause to `fallbackLevel`.
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 untrusted `feature` arg (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 first
Related
- `/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:
Read more
name: pdca-fast-track
classification: workflow
classification-reason: PDCA flow modifier — bypasses Checkpoint 1-8 user gates
deprecation-risk: none
effort: low
description: |
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
argument-hint: "<feature>"
user-invocable: true
allowed-tools:
- Read
- Write
- Glob
imports: []
next-skill: null
pdca-phase: null
task-template: "[Fast-Track] {feature}"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)
1. **Config enabled** — `bkit.config.json#control.fastTrack.enabled === true` 2. **Trust Score ≥ 80** — `.bkit/state/trust-profile.json#trustScore` ≥ `fastTrack.minTrustScore` (default 80) 3. **Design doc exists** — resolved via `bkit.config.json#pdca.docPaths.design` templates 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)
1. Recommend Automation Level escalation L2 → `fastTrack.autoLevel` (default `L3`). 2. 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": []
}3. Each Checkpoint 1-8 invocation calls `fast-track.recordCheckpoint` to append a decision entry (audit trail). 4. If a Checkpoint surfaces NO "Recommended" option, call `recordCheckpoint({ decision: 'fallback', reason: 'no_recommended' })` and pause to `fallbackLevel`.
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 untrusted `feature` arg (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 first
Related
- `/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:
A Claude Code plugin that verifies AI-generated code against its own design specs. Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software.
Repo: popup-studio-ai/bkit-claude-code
Other skills on bkit.
- /audit
View audit logs, decision traces, and session history for AI transparency. ACTION_TYPES (19 entries) include PDCA events (phase_transition, gate_passed/failed, agent_spawned/completed/failed, rollback_executed, destructive_blocked) and Sprint events (sprint_paused,
Open skill - /bkend-auth
bkend.ai authentication — email/social login, JWT tokens, RBAC, session management. Triggers: bkend auth, bkend login, bkend signup, bkend JWT, bkend RBAC
Open skill - /bkend-cookbook
bkend.ai project tutorials (todo to SaaS) and common error troubleshooting. Triggers: bkend tutorial, bkend cookbook, bkend troubleshooting
Open skill - /bkend-data
bkend.ai database — CRUD, column types, filtering, sorting, relations, indexing. Triggers: bkend table, bkend CRUD, bkend column, bkend relation, bkend data
Open skill - /bkend-quickstart
bkend.ai onboarding — MCP setup, resource hierarchy, tenant/user model, first project. Triggers: bkend quickstart, bkend onboarding, bkend setup, bkend MCP
Open skill - /bkend-storage
bkend.ai file storage — upload (presigned URL), download (CDN), visibility levels, buckets. Triggers: bkend file, bkend upload, bkend download, bkend storage, bkend presigned URL
Open skill

