CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-plans

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

61

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.agency/plugins/nori/skills/writing-plans/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.

The body is an efficient, actionable instruction skill: copy-paste templates for the plan header, test section, and footer, a sequenced required-step checklist, and concrete test-quality validation criteria. It falls short of top marks mainly on workflow integration (steps split between a todo list and guidelines, no feedback loop after presenting the plan) and mild redundancy in the zero-context assumption and test-checklist overlap.

Suggestions

Consolidate the three restatements of the zero-context assumption into one line in the Overview, and merge the test checklist with the adjacent system-reminder note since they largely duplicate each other.

Add one brief filled-in example of a testing-plan section so the template's expected level of specificity (mocks, boundaries, behavior) is unambiguous — this would raise actionability to 5.

Specify what happens after 'Present plan to user' (e.g., iterate on feedback, revise the plan before implementation) to close the workflow loop and lift workflow_clarity.

DimensionReasoningScore

Conciseness

The body is lean and instructional with no concept explanations Claude already knows, but has minor over-explanation that could be trimmed: the zero-context assumption is stated three times ('zero codebase context', 'zero context for our codebase', 'know almost nothing about our toolset'), and the test checklist partially restates the preceding system-reminder note about not testing mocks or data structures.

4 / 5

Actionability

It provides concrete, copy-paste-ready markdown templates for the plan header, testing plan, and footer, plus an explicit five-item test checklist with clearly marked placeholders. Not 5 because there is no worked example showing a filled-in plan or testing section, which the strongest anchor covers for common cases.

4 / 5

Workflow Clarity

The required todo block gives an explicit sequence (read guidelines, create plan, backwards compatibility, edge cases, open questions, testing emphasis, present to user) and the test checklist serves as validation checkpoints; no destructive or batch operations apply. Not 5 because the steps live in a todo list rather than a fully integrated workflow, and 'Present plan to user' lacks any feedback/iteration loop for handling user corrections.

4 / 5

Progressive Disclosure

The skill is a single well-organized file with clearly headed sections (Overview, Plan Document Header, Test Section, Plan Document Footer) and no external references, which is appropriate since none are needed. At roughly 93 lines it exceeds the under-50-line simple-skill exception, and no one-level-deep references are signaled, so it sits just below the top anchor.

4 / 5

Total

16

/

20

Passed

Description

67%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 specific, third-person, and answers both what the skill does and when to use it, with concrete deliverables (file paths, code examples, verification steps). Its main weakness is trigger-term coverage: it relies on one narrow trigger phrasing and omits the natural synonyms users would say when they need an implementation plan.

Suggestions

Add natural trigger variations users would actually say, e.g. 'Use when the user asks to write an implementation plan, break a design into engineering tasks, or spec out work for engineers' — this would lift trigger_term_quality and completeness toward 5.

Include concrete artifact/keyword anchors such as 'implementation plan document', 'task breakdown', or 'ticket-ready tasks' to broaden trigger matching and reduce overlap risk with general planning requests.

Tighten the redundant tail ('assuming engineer has minimal domain knowledge' repeats 'zero codebase context' from the same sentence) to free description budget for additional trigger phrases.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps' — in third-person voice, with only minor gaps in coverage. It names more than 1-2 actions but lacks the breadth of the 5-anchor's comprehensive multi-action coverage.

4 / 5

Completeness

Both 'what' (creates plans with file paths, code examples, and verification steps) and 'when' ('Use when design is complete and you need detailed implementation tasks') are explicitly present. Not 5 because the 'when' is a single trigger clause rather than multiple concrete trigger phrases; not 3 because the 'when' is explicit rather than weakly implied.

4 / 5

Trigger Term Quality

It includes some relevant keywords ('design is complete', 'implementation tasks', 'implementation plans') but misses common natural variations users would say, such as 'write an implementation plan', 'spec out tasks', 'break down the design into tickets', or 'plan the work'. Coverage is present but narrow relative to the 4-anchor's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche — post-design implementation planning for context-free engineers — that is mostly distinct from adjacent coding, review, or general planning skills, with only minor overlap risk against generic 'help me plan' requests.

4 / 5

Total

15

/

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
microsoft/FluidFramework
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.