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

66%

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

65%

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 clean, actionable routing overview with clear branches and an explicit review checkpoint, but it repeats key sentences, lacks inline feedback loops, and points to companion files that do not exist in the bundle.

Suggestions

Remove the duplicated 'source of truth' sentence and consolidate the repeated introduction of implementation-flow-guidance.md into a single pointer to tighten conciseness.

Add a short inline validate->fix->retry note for the routing decisions rather than fully deferring mechanics to companion files.

Ensure the referenced companion files (implementation-flow-guidance.md, chat-only-path-guidance.md, task-file-path-guidance.md) exist in the bundle, or replace the dead links with inline guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but it repeats itself ("Keep the approved active task as the source of truth" appears twice and "implementation-flow-guidance.md" is introduced repeatedly), so it could be tightened.	2 / 3
Actionability	Provides concrete, executable routing guidance with explicit decision branches and named file links (task-file path vs chat-only path, specific companion files to read), giving unambiguous next steps.	3 / 3
Workflow Clarity	Sequencing and an explicit validation checkpoint are present ("Before presenting work as ready, perform the `Implementation notes` check"), but the core mechanics are delegated to companion files and there is no inline feedback/retry loop for the routing decisions.	2 / 3
Progressive Disclosure	The overview is well-signaled with one-level-deep references to companion files, but the referenced bundle files (e.g. implementation-flow-guidance.md, chat-only-path-guidance.md, task-file-path-guidance.md) are not present in any bundle directory, so the disclosure structure is incomplete in practice.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 well-structured with explicit what-and-when triggers, but its trigger terms are jargon-heavy and the second-person voice plus overlap with sibling skills limit specificity and distinctiveness.

Suggestions

Rewrite in third person (e.g., 'Governs implementation-time routing...') to align with the rubric's voice expectation and recover the specificity score.

Add natural trigger phrasings a user would actually say (e.g., 'after a task is approved for implementation') alongside the bundle-internal terms.

Sharpen distinctiveness by contrasting the trigger condition (post-approval implementation) against the sibling plan/clarify skills it routes to.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and actions ("governs implementation-time routing, canonical task updates, and the final review checkpoint") but the action set is narrow; reduced from 3 to 2 because the description uses second-person voice ("Use this skill"), which the rubric penalizes.	2 / 3
Completeness	Clearly answers both what it does ("governs implementation-time routing, canonical task updates, and the final review checkpoint") and when to use it ("after execution approval for implementation work"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes an explicit trigger ("Use this skill after execution approval for implementation work") but leans on internal jargon ("chat-only or task-file task") and omits common natural phrasings a user would say.	2 / 3
Distinctiveness Conflict Risk	The post-approval implementation niche is fairly distinct, but the description shares heavy overlap with sibling spec-loop skills and the wording is specific to the bundle rather than to a unique user intent.	2 / 3
	Total	9 / 12 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: 741f932

Reviewed: 4 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.