epic

Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces an epic under the `tasks` role from AGENTS.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.

Quality

84%

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.

The body is a tightly structured specification skill: executable commands, a sequenced workflow with real validation checkpoints, and a complete output template. The only mild drag is some duplicated guidance across Rules/Instructions and an inline output template that could be a reference.

Suggestions

De-duplicate the frontmatter key list (rule 12) and the frontmatter shown in step 3 / Output Format into a single source of truth to trim tokens.

Consider moving the full markdown output template into a referenced file (or a clearly delimited 'Template' bundle) so the SKILL.md overview stays leaner.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic concept explanations), with minor over-explanation such as restating the same frontmatter requirements in both the Rules and the Instructions and Output Format sections.	4 / 5
Actionability	Concrete, executable guidance throughout: exact commands ('mkdir -p', 'date +%Y-%m-%d'), precise surgical-edit instructions for the SRS back-pointer, and a copy-paste-ready markdown output template covering the common case.	5 / 5
Workflow Clarity	An 8-step step_by_step workflow with explicit STOP-and-wait checkpoints (research questions, phase approval, critique selection) and a dedicated verification checklist with feedback loops (critique -> refine -> finalize).	5 / 5
Progressive Disclosure	Well-organized sections with a clear single-file overview and no nested references (no bundle files exist), but it leans toward inlining content (full output template, detailed step 7a) that keeps it just short of the ideal lean-overview profile.	4 / 5
	Total	18 / 20 Passed

Description

80%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.

The description is strong overall: it cleanly answers both what and when, uses third person, and draws a sharp boundary against the sibling 'plan' skill. Trigger-term coverage is the weakest dimension, relying on a few terms without synonyms or extensions a user would naturally say.

Suggestions

Add a few natural synonyms and concrete trigger phrases users actually say (e.g. 'roadmap', 'multi-phase feature', 'big project plan') to broaden trigger-term coverage, while keeping the existing negative boundary.

Consider naming one or two more concrete outputs (e.g. the per-phase status frontmatter or Definition-of-Done checklist) to lift specificity beyond 'several actions'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('produces an epic under the `tasks` role', 'dependency-ordered phases, atomic tasks, and per-phase status tracking') but stops short of enumerating the full breadth of what the skill produces, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' (produces an epic with dependency-ordered phases, atomic tasks, per-phase status) and 'when' with explicit trigger phrases ('Use when the user asks to plan a LARGE feature...') plus a contrasting 'Use plan for single-session tasks'.	5 / 5
Trigger Term Quality	Relevant keywords appear ('plan a LARGE feature', 'multiple sessions or phases', 'epic'), but the natural phrases a user would say are limited and lack common synonyms or file extensions.	3 / 5
Distinctiveness Conflict Risk	Narrow niche with explicit boundary guidance ('Do NOT trigger on generic planning, roadmap, or brainstorming requests'; 'Use plan for single-session tasks') minimizes conflict with the sibling plan skill.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing, 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/epic/SKILL.md
Commit: b4ba256

Reviewed: ~22 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.