CtrlK
BlogDocsLog inGet started
Tessl Logo

strategic-roadmap

Use when a user asks “what should I work on in this repo?”, “what’s worth doing next?”, repo audit, tech-debt priorities, architecture priorities, old-plan reconciliation, or repo-grounded opportunity discovery. Produces .agents/ROADMAP.md with generated opportunities, user-seeded ideas, Now/Next/Later sequencing, rejected/not-now items, and next-artifact recommendations. Not for standard product/release roadmaps; if multiple repos are requested, create one roadmap per repo.

72

Quality

87%

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

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.

The body is a tightly written, actionable senior-judgment playbook with a clean workflow and one real supporting template. It loses only marginal points for light redundancy between Workflow and Output Rules and for limited use of progressive disclosure beyond the single template reference.

Suggestions

Dedupe the constraints that appear in both Workflow and Output Rules (e.g., no implementation steps, no effort estimates) into one location to tighten conciseness.

Add a short 'Validate the roadmap' checkpoint in the Workflow (e.g., re-confirm each ranked item still has live evidence and every item names a next artifact) to push workflow_clarity toward a 5.

Consider extracting the audit-probe and ranking-heuristic lists into a reference file so SKILL.md reads as a leaner overview pointing to detail.

DimensionReasoningScore

Conciseness

The body is lean and directive, assuming Claude's competence and avoiding explanation of known concepts; minor redundancy between the Workflow steps and Output Rules (e.g., effort-estimation and no-implementation-steps guidance recurs) keeps it just below a 5.

4 / 5

Actionability

Concrete directives throughout — specific audit probes ('where the interface is nearly as complex as the implementation'), a ranking formula ('impact divided by likely effort, discounted by confidence and fix risk'), and an explicit next-artifact enumeration — with only minor abstraction in a few high-level instructions.

4 / 5

Workflow Clarity

A clear 5-step sequence with an explicit vetting checkpoint ('Verify every opportunity you rank by opening the cited code, plan, or artifact yourself; subagent output and old plans are leads, not evidence'); no destructive/batch cap applies to this doc-writing skill, but checkpoints are less formalized than a validate-then-proceed loop.

4 / 5

Progressive Disclosure

Well-structured sections with a clearly signaled, one-level-deep reference to references/roadmap-template.md (verified to exist); the body keeps most guidance inline, which is appropriate but leaves only one external reference, a notch below the ideal split.

4 / 5

Total

16

/

20

Passed

Description

100%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 is a strong, complete trigger: it states concrete outputs, uses natural quoted user phrasings, covers both what and when explicitly, and disambiguates itself from standard roadmapping skills. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete outputs — 'Produces .agents/ROADMAP.md with generated opportunities, user-seeded ideas, Now/Next/Later sequencing, rejected/not-now items, and next-artifact recommendations' — giving comprehensive coverage of what the skill produces.

5 / 5

Completeness

Explicitly answers both: 'when' via the 'Use when a user asks…' clause with concrete trigger phrases, and 'what' via 'Produces .agents/ROADMAP.md with…'.

5 / 5

Trigger Term Quality

Quoted natural user phrases ('what should I work on in this repo?', 'what's worth doing next?') plus synonyms (repo audit, tech-debt priorities, architecture priorities, old-plan reconciliation) cover the full range of how a user would request this.

5 / 5

Distinctiveness Conflict Risk

Carves out a clear niche with an explicit boundary ('Not for standard product/release roadmaps') and distinct repo-grounded-discovery triggers, minimizing conflict with adjacent skills.

5 / 5

Total

20

/

20

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
joshuadavidthomas/agent-skills
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.