CtrlK
BlogDocsLog inGet started
Tessl Logo

accord

Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision, L1 Requirements, L2 Team Detail, L3 Acceptance Criteria). Use for cross-team specs.

55

Quality

61%

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 ./.archive/accord/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%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 well-structured and workflow-oriented but undermined by verbosity, citation padding, and a progressive-disclosure map pointing to reference files that are absent from the bundle. Tightening prose and either shipping or removing the missing references would lift the weaker dimensions.

Suggestions

Trim the HTML capability/collaboration comment and the embedded citation prose (CMU SEI, Wiley SLR, Cucumber anti-pattern rationale) — keep only the actionable rule, since Claude already knows these concepts.

Fix the Workflow table header (merge 'Required result' and 'Read' into two clean columns) and the repeated/duplicated rules across Boundaries and Critical Decision Rules.

Either include the referenced reference/*.md and _common/*.md files in the bundle or replace the dangling links with the minimal inline content needed to act, so progressive disclosure resolves at the first hop.

DimensionReasoningScore

Conciseness

The body is noticeably verbose: a large HTML capability/collaboration comment duplicates content restated later, and several rules carry padded citations and explanations Claude already knows (CMU SEI defect stats, Wiley SLR percentages, Cucumber anti-pattern prose).

2 / 5

Actionability

Recipes, subcommands, scope thresholds, and canonical ID schemes provide concrete guidance, but most executable detail is deferred to reference/*.md and _common/*.md files that are not present in the bundle, leaving gaps a reader cannot resolve.

3 / 5

Workflow Clarity

The ALIGN→STRUCTURE→ELABORATE→BRIDGE→VERIFY→DELIVER sequence is clearly ordered with validation checkpoints (VERIFY phase, Three Amigos review, traceability thresholds), though the workflow table header/columns are malformed ('Required result Read').

4 / 5

Progressive Disclosure

Content is structured as an overview with well-signaled, one-level-deep references via the Reference Map, but none of the ~17 referenced reference/ or _common/ files actually exist in the bundle, so the navigation collapses at the first hop.

3 / 5

Total

12

/

20

Passed

Description

75%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 third-person, concrete, and answers both 'what' and 'when' with explicit trigger guidance. It is solid but not maximal — the 'when' clause is brief and a few natural synonyms are missing.

DimensionReasoningScore

Specificity

Lists several concrete elements — audiences (Business/Development/Design) and staged elaboration stages (L0 Vision, L1 Requirements, L2 Team Detail, L3 Acceptance Criteria) — giving broad, concrete coverage of what the skill does.

4 / 5

Completeness

Explicitly states both what it does (authoring unified specification packages via staged elaboration) and when to use it ('Use for cross-team specs'), but the 'when' clause is terse and could be more specific about trigger scenarios.

4 / 5

Trigger Term Quality

Includes natural phrases a user might say ('cross-team specs', 'Business/Development/Design', 'specification packages') but misses common synonyms and file-extension-style triggers that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

The cross-team unified-package niche with staged elaboration is distinct from generic doc skills, with only minor overlap risk against Scribe-style formal-spec skills.

4 / 5

Total

16

/

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
simota/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.