CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

writing-plans

Write a detailed implementation plan for a feature, spec, or ticket, breaking the work into bite-sized, testable tasks with exact file paths, code samples, and test commands an engineer can follow step by step. This is the internal planning stage of the delivery-flow workflow, run after delivery-flow splits the work into multiple meaningful implementation units. It is not a standalone entry point, so do not activate it directly for a one-off user request or a narrow change; use delivery-flow for those instead.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tessleng/sdlc-planning

SKILL.md
Quality
Evals
Security

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.

Excellent instructional content: fully actionable templates, an explicit self-review validation loop, and a clear process order, all with minimal padding. The only refinement opportunities are trimming a few rationale sentences and considering whether the large always-needed templates justify the skill's inline length.

Suggestions

Trim explanatory rationale (e.g., the 'You reason best about code you can hold in context at once' sentences in File Structure) to pure directives — the guidance stands without the justification.

Consider moving the Plan Document Header and Task Structure templates into a references/ file (e.g., references/plan-template.md) to keep SKILL.md a lean overview, since the templates are reproduced verbatim each run.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no teaching of known concepts ("DRY. YAGNI. TDD. Frequent commits."), and templates carry real content. A 4 rather than 5 because a few rationale sentences ("You reason best about code you can hold in context at once, and your edits are more reliable when files are focused") and the extended placeholder list could be tightened.

4 / 5

Actionability

Everything is executable: exact save path (docs/plans/YYYY-MM-DD-<feature-name>.md), copy-ready plan-header and task templates with concrete test/commit commands (pytest … -v, git commit -m), and a hard placeholder blacklist. Guidance is copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

The lifecycle is clearly sequenced (Scope Check → File Structure → task right-sizing → templates → Self-Review → Execution Handoff) with an explicit validation checklist (spec coverage, placeholder scan, type consistency) and a fix-loop ("If you find issues, fix them inline… If you find a spec requirement with no task, add the task"). Matches the top anchor's checklist-plus-feedback-loop pattern.

5 / 5

Progressive Disclosure

A single-file skill (no references/, scripts/, or assets/ exist) with well-organized sections and no nested references; the templates are needed on every invocation so inlining is defensible. A 4 rather than 5 because the two large template blocks (Plan Document Header, Task Structure) could arguably live in a reference file, and the skill is over the ~50-line threshold where section organization alone would justify a 5.

4 / 5

Total

18

/

20

Passed

Description

92%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 strong description: concrete about deliverables, explicit about when it applies and when it does not, and clearly scoped as a nested stage of delivery-flow. The only weakness is modest keyword coverage — a few natural synonyms for planning requests are missing.

DimensionReasoningScore

Specificity

The description comprehensively specifies concrete outputs: "breaking the work into bite-sized, testable tasks with exact file paths, code samples, and test commands an engineer can follow step by step" covers every deliverable of the planning task. Not a 4 because there are no gaps in the coverage of what the skill produces.

5 / 5

Completeness

Both questions are answered explicitly: the "what" (detailed plan with tasks, file paths, code samples, test commands) and the "when" ("run after delivery-flow splits the work into multiple meaningful implementation units… do not activate it directly for a one-off user request or a narrow change; use delivery-flow for those instead"). The explicit trigger guidance means the missing-'Use when' cap does not apply; a 4 would require the when-clause to be less specific than it is.

5 / 5

Trigger Term Quality

Natural terms are present — "implementation plan", "feature, spec, or ticket", "planning stage" — and would match how a user phrases the need. Not a 5 because common variations like "task breakdown", "break down the work", or "design doc" are absent; not a 3 because the existing keyword set is good rather than merely partial.

4 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche ("the internal planning stage of the delivery-flow workflow") and actively de-conflicts by directing one-off and narrow requests to delivery-flow. Minimal risk of triggering for the wrong skill, matching the top anchor.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tesslio/tessl-eval-demo

Path

00-activation-testing/before/plugins/sdlc-planning/skills/writing-plans/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.