todo

Search the entire codebase for TODO markers and create a markdown document with proposed next steps for each.

Quality

50%

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 ./.github/skills/todo/SKILL.md

Quality

Content

50%

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 well-organized, genuinely actionable instruction-only workflow that avoids padding, but it lands at an adequate level on every dimension due to redundant field listings, an abstract search step without an executable command, no in-flow validation for a batch operation, and no progressive disclosure beyond a single inline file. It is solid and usable without reaching the anchors that reward tightness, executable guidance, explicit checkpoints, or file-based disclosure.

Suggestions

Give a concrete executable search command (e.g. `rg -n --hidden -g '!node_modules' -g '!dist' 'TODO' .`) so the core step is copy-paste ready rather than abstract.

De-duplicate the capture-field list between "What To Capture" and "Produce Markdown Document" by defining the fields once and referencing them in the report structure.

Add an in-flow validation checkpoint for the batch search, e.g. after dedup verify that distinct TODOs were not collapsed and that every required field is populated before drafting the report.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the per-TODO capture fields (file/line/excerpt/next-step/priority) are listed twice across "What To Capture" and "Produce Markdown Document", and the example enums are long enough that the text could be tightened.	2 / 3
Actionability	Guidance is specific throughout (concrete TODO variants, ignore dirs, capture fields, categorization taxonomy, report structure), but the core search step is abstract ("Run a repo-wide search for TODO markers") with no executable command such as a ripgrep/grep invocation.	2 / 3
Workflow Clarity	The procedure is a clear numbered 1-5 sequence with a dedup step and a terminal Pass Criteria checklist, but as a batch whole-repo operation it lacks an in-flow validation or feedback loop, which the rubric caps at 2.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but at ~117 lines (over the 50-line simple-skill threshold) the content is entirely inline with no references or offloading of detail to bundle files.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 concrete and on-domain but settles for an adequate level across every dimension: it states what the skill does without explicit trigger guidance and with only a narrow set of actions. It is clearly better than vague boilerplate but stops short of the anchors that require comprehensive actions and explicit "Use when..." triggers.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to extract a backlog from inline TODO comments, triage technical debt, or audit unfinished work before a release."

Broaden natural trigger terms to include variations users actually say: "TODOs", "technical debt", "backlog", and "unfinished work".

Expand the action list to reflect the full workflow (search, deduplicate, categorize by type, propose next steps, generate a markdown report) so specificity reads as comprehensive.

Dimension	Reasoning	Score
Specificity	Names the TODO-marker domain and two concrete actions ("Search the entire codebase", "create a markdown document with proposed next steps"), but the action set is narrow and omits categorize/dedup/priority that the body actually covers, so it is not comprehensive.	2 / 3
Completeness	Clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Includes the canonical natural term "TODO markers" plus "codebase" and "markdown", but misses common variations a user would say such as "technical debt", "backlog", or "unfinished work".	2 / 3
Distinctiveness Conflict Risk	The TODO-plus-next-steps niche is recognizable, but with no explicit triggers the generic "search the codebase" action could overlap with general code-search or audit skills.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: vladmandic/sdnext
Path: .github/skills/todo/SKILL.md
Commit: 058a7f0

Reviewed: about 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.