CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

project-management

Load to plan a cycle, audit issues, build a roadmap, or decompose research into issues.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/project-management/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 tightly written policy and dispatch document: every sentence carries a rule, commands and output formats are copy-paste concrete, and validation checkpoints (preflight, halt-on-failure, approval gates, verify-before-report) guard the batch tracker mutations. The main gaps are unresolved in-bundle references to workflow/template/schema files, an orphaned local script, and a few over-compressed paragraphs that pack many rules into single sentences.

Suggestions

Resolve the dangling references: either include the cited workflows/, templates/, and schemas/ files in the bundle or state explicitly that they live in the parent package, so a reader in this bundle can follow every link.

Reference scripts/verification-scope from the body (e.g. in the Contracts table's Tracker CLI rows) so the bundled script is discoverable.

Split the single-paragraph post-merge Done-when rules into a short list (or move the format spec to a reference file) to reduce re-reading cost without adding tokens.

DimensionReasoningScore

Conciseness

Dense, rule-only prose with zero padding and no explanation of concepts Claude already knows (e.g. "File an issue only when all three hold"). Not 5: the ~20-rule single paragraph on post-merge Done-when boxes, and scope rules repeated across Execution Rules and Scope by Path, could be consolidated.

4 / 5

Actionability

Gives exact commands ("issues update [ISSUE_ID] --attach [PATH]", "gh issue view [N] --repo [OWNER/REPO] --json body,comments") and copy-paste templates (the "- [ ] Post-merge: <check>; Where: ...; Trigger: ...; Deadline: ..." line format). Not 5: several mechanics (e.g. --review-born semantics, workflow step detail) delegate to files not present in this bundle.

4 / 5

Workflow Clarity

Sequencing is explicit ("Run workflow sections in order. Skip only on an explicit **Skip if** condition") and batch/destructive tracker mutations have validation checkpoints: the label preflight that "halts before mutation", the "failed read halts the workflow" rule, the "Verify every attachment and description write before reporting completion" step, and the § 6 approval gate. Not 5 because the actual per-workflow step sequences live in external workflow files rather than in this document.

4 / 5

Progressive Disclosure

Structure is well signaled: the Commands, Contracts, and "Where each rule lives" tables state what each referenced file contains, and all three cited references/*.md files exist one level deep. Not 5: the body cites workflows/*.md, templates/*.md, and schemas/*.md paths that do not exist in this bundle, and the local scripts/verification-scope has no inbound reference from the body.

4 / 5

Total

16

/

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.

A concise, action-oriented description that names four distinct capabilities and stays well within token budget. Its main weakness is the absence of an explicit trigger clause — when to load the skill is only implied by "Load to..." — and it lacks common synonyms such as "backlog" or "project planning" that a user might naturally say.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to plan a work cycle, audit an issue backlog, build a roadmap, or break research down into issues."

Include common user-side synonyms ("backlog", "project planning", "triage/prioritize") so the description matches how users actually phrase these requests.

Briefly disambiguate domain jargon such as "cycle" (e.g. "plan a work cycle") so the trigger is understandable outside the package's own vocabulary.

DimensionReasoningScore

Specificity

Names four concrete actions ("plan a cycle", "audit issues", "build a roadmap", "decompose research into issues") with only minor coverage gaps. Not 5 because it omits capabilities the body exposes (project ordering, research completion, issue disposition).

4 / 5

Completeness

The "what" is clear (four stated actions), but there is no explicit "Use when..." clause or equivalent trigger guidance — "Load to..." only weakly implies when, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"audit issues", "roadmap", "plan", and "decompose research" are natural entry phrases, though "cycle" is package jargon. Not 5 because common synonyms like "backlog", "project planning", "prioritize", and "triage" are missing.

4 / 5

Distinctiveness Conflict Risk

"audit issues", "build a roadmap", and "decompose research" are distinctive to TPM/tracker planning with only minor overlap risk against generic planning skills. Not 5 because "plan a cycle" alone could collide with other planning workflows.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 28 missing, 9 suspicious

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/project-management/SKILL.md

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.