spec-loop-implementation-flow

Use this skill after execution approval for implementation work in an approved chat-only or task-file task. It governs implementation-time routing, canonical task updates, and the final review checkpoint.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/spec-loop-implementation-flow/SKILL.md

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 tight, highly actionable routing skill with a clear sequenced workflow, an explicit review checkpoint, and feedback loops for ambiguous cases. The only real weakness is progressive disclosure: the detail files it points to are not present in the bundle, so the well-signaled references lead to missing targets.

Suggestions

Include the referenced bundle files (implementation-flow-guidance.md, chat-only-path-guidance.md, task-file-path-guidance.md) in references/ so the one-level-deep navigation actually resolves.

Remove the restated opening line and the duplicate 'Keep the approved active task as the source of truth' sentence to tighten conciseness to a 5.

Confirm the spec-loop-plan-task and spec-loop-clarify-task sibling SKILL.md links resolve from the bundle root so external navigation is complete.

Dimension	Reasoning	Score
Conciseness	The body is lean, bullet-driven, and assumes Claude's competence without explaining concepts, but the 'Use this skill after execution approval...' lead and 'Keep the approved active task as the source of truth' line are restated from the frontmatter and core rules, leaving minor instances that could be trimmed; this fits 'efficient; minor instances of over-explanation' rather than the fully lean 5.	4 / 5
Actionability	Despite being instruction-only with no code, the guidance is fully actionable: it names exactly which files to read, how to choose the active path (task-file vs chat-only), which companion to read per path, and the concrete decision points and routing destinations, matching 'fully executable; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The workflow is clearly sequenced (core rules -> read and path selection -> choose path -> read companion -> Implementation notes checkpoint -> review) with an explicit validation checkpoint ('Before presenting work as ready, perform the Implementation notes check') and feedback loops for error cases (conflict -> stop and ask; unclear increment -> return to plan-task), matching the 'clear sequence with explicit validation steps; feedback loops' anchor.	5 / 5
Progressive Disclosure	The body is a clean overview with well-signaled one-level-deep references (spec-loop-plan-task, spec-loop-clarify-task, implementation-flow-guidance, and the two path companions) and clear navigation per file, but the referenced detail files (implementation-flow-guidance.md, chat-only-path-guidance.md, task-file-path-guidance.md) are not present in the bundle (references/scripts/assets are absent), so navigation is structurally sound but incomplete, fitting 'good structure; minor organization gaps' rather than the fully navigable 5.	4 / 5
	Total	18 / 20 Passed

Description

66%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 clearly scopes a distinct niche and answers both what and when, but its trigger terms are bundle-internal jargon and its stated actions are governance-level abstractions rather than concrete capabilities. Tightening the phrasing toward natural user language and concrete operations would lift the mid-range dimensions.

Suggestions

Reword the 'when' clause using natural user-facing phrasing (e.g., 'Use when implementing an approved task increment') rather than bundle jargon like 'execution approval' and 'chat-only or task-file task'.

Make the 'what' more concrete by naming the actual operations performed (e.g., 'routes implementation work, updates the canonical task, and runs the review checkpoint') instead of abstract governance language.

Add a couple of natural trigger synonyms (e.g., 'implementing', 'coding the approved plan', 'finishing an increment') so the description matches how users actually request this work.

Dimension	Reasoning	Score
Specificity	Names the domain ('implementation work in an approved chat-only or task-file task') and three governed areas ('implementation-time routing, canonical task updates, and the final review checkpoint'), but these are governance-level abstractions rather than concrete user-facing actions, fitting the '1-2 concrete actions, not comprehensive' anchor and falling short of the multi-action comprehensiveness of a 4.	3 / 5
Completeness	Explicitly answers both what ('governs implementation-time routing, canonical task updates, and the final review checkpoint') and when ('Use this skill after execution approval for implementation work in an approved chat-only or task-file task'), but the 'when' is technical rather than the concrete trigger phrasing required for a 5.	4 / 5
Trigger Term Quality	Contains relevant keywords ('implementation work', 'after execution approval', 'chat-only or task-file task') but these are bundle-specific jargon rather than the natural phrases a user would say, and common variations/synonyms are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ('after execution approval', 'chat-only or task-file task' within the spec-loop bundle) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-implementation-flow/SKILL.md
Commit: 27df5cc

Reviewed: 19 days 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.