synaptiai/bdsk/accept
Claude Code and agent skill by synaptiai/bdsk
- community
Checking that the SKILL.md file is still in the repository.
Compute acceptance eligibility per BDSK Algorithm E. Checks verification coverage, execution evals, gate status, and authority. Generates an acceptance_decision artifact. Use after /validate passes.
Install
npx vskill@latest install synaptiai/bdsk/acceptSKILL.md
/accept
Compute acceptance eligibility and generate an acceptance_decision.
Process
- Run /validate first. If validation has not been run, tell the user to run
/validatefirst.
- Check Algorithm E conditions. For the active execution plan, verify:
a. Required verification artifacts exist and pass (execution_result: pass) b. Required execution evals exist (if any review gates are defined) c. No unwaived blocking gate failures remain d. No unresolved manual-review or escalation gates remain e. No unresolved stop-condition breaches remain f. Acceptance is approved by required authority
- Compute outcome:
- If all 6 conditions pass:
accepted - If blocking conditions pass but non-blocking warnings remain:
conditionally_accepted - If any required dependency is unresolvable:
indeterminate - Otherwise:
rejected
- Present findings. Show the user which conditions passed and which failed.
- Write the acceptance decision artifact. Always record the decision, regardless of outcome:
- Clean up active execution state. If outcome is
acceptedorconditionally_accepted, remove the execution plan from.claude/state/active-executions/. Ifrejected, leave the active execution in place so the user can fix issues and re-run.
- Write to disk. Save to
artifacts/acceptance/<id>.yaml
Rules
- Never record
acceptedif any blocking condition fails - When outcome is
acceptedand all 6 conditions pass: record automatically without asking - When outcome is
conditionally_accepted,rejected, orindeterminate: present findings to user and ask for their decision - The user's explicit approval is required only when the outcome is not clean
accepted - If
conditionally_accepted, conditions array MUST be non-empty - When invoked from /run, follows the same auto-accept-on-success principle
Schema Compliance
- spec has exactly 6 fields:
subject_diffs,decision_summary,reasons,conditions,residual_risks,approvers. No additional fields. Schema usesadditionalProperties: false. - metadata has exactly 1 field:
outcome(enum:accepted,rejected,conditionally_accepted). No additional fields. - Trace refs MUST be
{target_id: <id>, edge: <edge>}objects, not bare string IDs. - Approvals MUST use
{authority_role: <role>, approver: <user>, approved_at: <ISO-8601>}. Not{date, decision}. - Valid authority roles (5 total):
product_authority,technical_authority,security_authority,release_authority,qa_authority.
Edge-kind rules for acceptance_decision
- Upstream
depends_on→ generated_diff, verification_artifact, execution_eval, waiver_record - Do NOT link to execution_plan (not in compatibility matrix for acceptance_decision)
- Do NOT link to behavior_spec or assumption_record
- Do NOT use
evaluatesedge — acceptance_decision only usesdepends_on
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/accept/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/synaptiai/bdsk/accept)