CtrlK
BlogDocsLog inGet started
Tessl Logo

epic-resolution

Closeout protocol for parent epics — answers "we resolved all epic subs, are we done now?" with a structured matrix + verdict recommendation (close / keep open / create missing subs / retire-supersede). Sibling to epic-review (which handles entry); this is the exit gate. Triggers: Use this skill when the last required sub of an epic closes, when a team member claims an epic is complete or substrate-side complete, before closing an epic as COMPLETED, or when a peer broadcasts an epic-readiness signal that needs reconciliation against parent ACs.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

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

The body is an extremely lean, well-structured redirect that excels at conciseness and progressive disclosure, but it delegates the entire actionable workflow to the reference, leaving in-body actionability and workflow sequencing thin.

Suggestions

Add a brief 2–3 line skeleton of the workflow in the body (e.g. 'populate AC→sub matrix → reconcile delivered vs required evidence → emit verdict: close/keep open/create missing subs/retire-supersede') so the skill is partially actionable without opening the reference.

Surface one concrete validation checkpoint inline — such as 'confirm no RESIDUAL_L4 ACs or BLOCKER subs remain before recommending close' — to give the body a gating step rather than only a redirect.

Include a one-line example of the verdict output format so a reader can recognize the expected result without reading the full reference.

DimensionReasoningScore

Conciseness

The body is a single lean paragraph that assumes Claude's competence and contains no padding or restated concepts, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

It gives one concrete executable instruction ('use the view_file tool to read ... epic-resolution-workflow.md') but no examples and the actual workflow guidance is delegated to the reference, leaving the body incomplete on its own.

2 / 3

Workflow Clarity

The gating action is unambiguous ('before posting any verdict or recommendation') but the multi-step matrix/verdict workflow is entirely offloaded with no in-body sequence or validation checkpoints.

2 / 3

Progressive Disclosure

The body is a clear overview pointing to one real, well-signaled, one-level-deep reference (verified to exist at references/epic-resolution-workflow.md), which is textbook progressive disclosure.

3 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 across all dimensions: it states concrete actions, includes an explicit trigger clause, and clearly distinguishes the skill from its sibling. It uses third person and is concise without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'structured matrix + verdict recommendation (close / keep open / create missing subs / retire-supersede)' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (closeout protocol producing a matrix + verdict) and when via an explicit 'Triggers: Use this skill when...' clause, matching the top anchor.

3 / 3

Trigger Term Quality

The 'Triggers: Use this skill when...' clause covers natural domain phrases a user would say ('last required sub of an epic closes', 'claims an epic is complete', 'peer broadcasts an epic-readiness signal'), giving good coverage.

3 / 3

Distinctiveness Conflict Risk

Explicitly carves a niche as 'the exit gate' and distinguishes it from sibling 'epic-review (which handles entry)', making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
neomjs/neo
Reviewed

Table of Contents

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.