orchestrate-epic

Use when you have a multi-ticket epic (many related tickets across repos) and want to work as many as possible in parallel without breaking dependencies, or need to know what is unblocked now — ingest the epic and its child tickets, build the dependency graph from both formal links and free-text "Dependencies" notes, compute a parallel wave schedule, then act as a persistent coordinator that spawns a session per workable ticket and re-verifies what unblocked as tickets finish.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced coordinator skill with strong validation feedback loops and concrete executable commands. The main weakness is redundancy between the Common Mistakes and Red flags sections, which inflates token cost without adding information.

Suggestions

Collapse 'Common Mistakes' and 'Red flags — STOP if you think' into one section; they cover the same five points and the repetition is pure token cost.

Move the per-ticket context brief template and the eligibility rule prose into a short referenced file (e.g. references/brief-format.md) to slim the main body.

Dimension	Reasoning	Score
Conciseness	Dense and operational, assuming Claude's intelligence (no explaining of Jira or dependency graphs), but the 'Common Mistakes' and 'Red flags' sections substantially restate the same points (links-empty, verify-done, per-dimension trust, use schedule.py, stay resident), which is trimmable redundancy.	4 / 5
Actionability	Provides copy-paste-ready, executable guidance: the schedule.py bash invocation with fallback find, the exact scheduler input JSON shape, exit-code handling (0/10/1), the `mcp__ccd_session__spawn_task` field spec, and a concrete per-ticket brief template.	5 / 5
Workflow Clarity	Phases A–F are clearly sequenced with a mermaid flowchart and explicit validation checkpoints: preflight dependency check, exit-code feedback loops (cycle → ask user to break; malformed → fix and re-run), and mandatory re-verification of 'done' claims against Jira + MR before advancing a wave.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with one-level-deep external references (lib/schedule.py, requirements.json, sibling devflow skills) and no nested-reference chains, but it is a single ~190-line file where some material (eligibility rules, brief template) is inlined rather than split into reference files.	4 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, comprehensive description that clearly states both capability and trigger conditions for a well-scoped niche. The only deduction is the second-person trigger voice, which the rubric penalizes on specificity.

Suggestions

Rewrite the trigger in third person to avoid the voice penalty, e.g. 'Use when coordinating a multi-ticket epic... ingests the epic and child tickets, builds the dependency graph...'.

Add a couple of natural synonyms (e.g. 'parallelize', 'schedule', 'blocked/unblocked tickets') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('ingest the epic and its child tickets, build the dependency graph from both formal links and free-text notes, compute a parallel wave schedule, spawn a session per workable ticket and re-verifies what unblocked'), which is 5-level coverage, but the second-person trigger voice ('Use when you have...', 'want to work') triggers the -1 voice penalty per the rubric.	4 / 5
Completeness	Explicitly answers both what (ingest, build graph, compute schedule, coordinate/spawn, re-verify) and when ('Use when you have a multi-ticket epic... want to work as many as possible in parallel... or need to know what is unblocked now') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('multi-ticket epic', 'parallel', 'dependencies', 'unblocked', 'child tickets') that a user would plausibly say, but it leans jargon-heavy and omits some common synonyms; not quite the comprehensive 5-level set.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — cross-repo multi-ticket epic coordination with parallel wave scheduling and resident re-verification — with triggers unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AndreJorgeLopes/devflow
Path: devflow-plugin/skills/orchestrate-epic/SKILL.md
Commit: bd4b70c

Reviewed: 7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.