CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spec-writing

Execute this skill should be used when the user asks about "writing specs", "specs.md format", "how to write specifications", "sprint requirements", "testing configuration", "scope definition", or needs guidance on creating effective sprint specifications for agentic development. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

73%

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 ./plugins/community/sprint/skills/spec-writing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured, highly actionable authoring guide: concrete paths, enumerated settings, troubleshooting table, and two complete example specs. Its main weaknesses are the missing links to two of the three reference files (examples.md is duplicated inline rather than cited, errors.md is orphaned) and minor duplication of testing-configuration.md guidance in steps 4-5.

Suggestions

Link the bundle's examples.md from the Examples section (e.g., 'More annotated examples: ${CLAUDE_SKILL_DIR}/references/examples.md') and either shrink the inlined examples or move the bulk of them into examples.md to avoid duplicating its content.

Deduplicate steps 4-5 by moving the when-to-use guidance into testing-configuration.md (which already covers it) and keeping one summary line plus the reference in the body; also resolve errors.md — either link it from Error Handling or remove it from the bundle since its generic content is unrelated to this skill.

DimensionReasoningScore

Conciseness

The body is lean: concrete instructions, a compact error table, and no explanation of concepts Claude already knows. Minor trimming possible — steps 4 and 5 duplicate the 'when to use each setting' guidance already in testing-configuration.md, which is the only thing keeping it from the leanest anchor.

4 / 5

Actionability

Fully executable for an instruction-only skill: the concrete path '.claude/sprint/[N]/specs.md', enumerated setting values ('QA: required | optional | skip', 'UI Testing Mode: automated | manual'), and two complete copy-paste-ready example specs covering the common backend-with-QA and frontend-only cases.

5 / 5

Workflow Clarity

A clear 7-step sequence (goal → scope → testing config → setting guidance → minimalism → iteration) with an Error Handling table mapping failures to fixes, plus the examples acting as checklists. Not a 5 because the final validation step is implicit — there is no 're-read the spec for ambiguity before handing to the architect' checkpoint, only the error table after the fact.

4 / 5

Progressive Disclosure

testing-configuration.md is well signaled via '${CLAUDE_SKILL_DIR}/references/testing-configuration.md' in both the instructions and Resources, but the other two bundle files are orphaned: examples.md (richer, annotated examples) is never referenced and its content is substantially duplicated by the inlined Examples section, and errors.md is also unlinked. Content that belongs in a reference is inlined while the reference file goes undiscoverable — matching the 'could be better organized / content that should be separate is inline' anchor.

3 / 5

Total

16

/

20

Passed

Description

56%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 has solid natural trigger phrases and a distinct core niche, but the capability statement ('guidance on creating effective sprint specifications') is vague, and the opening 'Execute this skill should be used when...' is grammatically broken. The filler sentences 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' add no information. It reads as a trigger list missing a crisp what-the-skill-does statement.

Suggestions

Fix the broken opening and state the capability concretely, e.g.: 'Provides guidance on authoring effective specs.md files for the Sprint plugin: writing concise goal statements, defining In Scope/Out of Scope boundaries, and configuring QA and UI testing settings.'

Delete the meta-filler sentences 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' — they add no trigger value and pad the description.

Add a couple of missing natural synonyms such as "spec" or "sprint specs" and trim overly generic triggers like "testing configuration" and "scope definition" that risk firing for unrelated skills.

DimensionReasoningScore

Specificity

The only stated capability is 'needs guidance on creating effective sprint specifications for agentic development' — one generic action with the domain named. No concrete actions are enumerated (no mention of writing goal statements, scope boundaries, or testing configuration), matching the 'names the domain but actions are minimal or generic' anchor rather than the 1-2-concrete-actions level.

2 / 5

Completeness

The 'when' is explicit (quoted trigger phrases), but the 'what' is only the vague 'guidance on creating effective sprint specifications' with no concrete capability statement. This sits between the clear-what/weak-when anchor and the both-present anchor; the under-specified 'what' holds it at 3.

3 / 5

Trigger Term Quality

Good natural-phrase coverage: "writing specs", "specs.md format", "how to write specifications", "sprint requirements", "testing configuration", "scope definition". A few natural terms are missing (e.g., "spec", "requirements doc", "sprint specs"), so it falls just short of the comprehensive synonym/extension level.

4 / 5

Distinctiveness Conflict Risk

Core triggers like "specs.md format" and "sprint specifications" occupy a clear niche, but "testing configuration" and "scope definition" are generic enough to overlap with testing-setup or general-scoping skills — minor overlap risk consistent with the 'mostly distinct' anchor.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/community/sprint/skills/spec-writing/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.