epic

Use when the user asks to plan a LARGE feature spanning multiple sessions or phases — produces an epic under the `tasks` role with dependency-ordered phases, atomic tasks and per-phase status. Use plan for single-session tasks, not for roadmaps.

Quality

80%

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

73%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 thorough, well-sequenced instruction skill with strong workflow guardrails and a concrete output template. The main cost is cross-section repetition that inflates the token budget without adding new information.

Suggestions

Consolidate the repeated frontmatter-shape and phase-size constraints into a single canonical location (e.g. Rules) and reference it from the Instructions and Verification sections to reduce duplication.

Consider moving the detailed Question Format spec into a one-level reference file so SKILL.md stays a lean overview.

In step 2, inline the specific AGENTS.md rules being deferred to (or quote the operative lines) so the skill remains actionable when AGENTS.md is not immediately at hand.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and directive with no concept-explanation padding, but constraints recur across the Rules, Instructions, Output Format, and Verification sections (e.g. frontmatter shape, phase-size limits) and could be tightened.	3 / 5
Actionability	Provides highly concrete guidance — exact frontmatter keys, `date +%Y-%m-%d` / `mkdir -p` commands, a surgical-edit procedure in step 7a, and a copy-paste output template — with minor reliance on external AGENTS.md rules.	4 / 5
Workflow Clarity	An 8-step numbered process with explicit STOP-and-wait checkpoints, a critique→refine feedback loop, idempotency guards on the surgical SRS edit, and a closing verification checklist covering the destructive write operations.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Overview, When to Use, Context, Rules, Instructions, Output Format, Verification) with no nested references, though as a 230-line single file it could offload some detail (e.g. the question-format spec) into a one-level reference.	4 / 5
	Total	16 / 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, third-person description that clearly states both capability and trigger conditions while explicitly contrasting with adjacent skills. Minor room to expand the concrete action list and natural-term synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "produces an epic under the `tasks` role with dependency-ordered phases, atomic tasks and per-phase status" — but stops short of the fully comprehensive action list that would warrant a 5.	4 / 5
Completeness	Explicitly answers both what ("produces an epic ... with dependency-ordered phases, atomic tasks and per-phase status") and when ("Use when the user asks to plan a LARGE feature spanning multiple sessions or phases") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ("plan a LARGE feature", "multiple sessions or phases", "epic", "roadmaps") a user would actually say, with a few common variants (e.g. "break down", "split work") absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (large multi-session features) and actively disambiguates from siblings via "Use plan for single-session tasks, not for roadmaps", minimizing wrong-skill triggering.	5 / 5
	Total	18 / 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: 78c7f17

Reviewed: 2 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.