CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

context-and-decisions

Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require repeated explanation, one term has multiple meanings, unclear language causes module-boundary mistakes, or domain semantics must remain separate from architecture decisions.

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 ./.agents/skills/context-and-decisions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers concrete, boundary-aware instruction with a clear sequenced workflow and genuine approval/validation checkpoints, appropriate for an instruction-only skill. Its main weaknesses are structural redundancy across the "When to Activate"/"When to Use"/"How It Works" summary sections and a twice-referenced template file that is missing from the bundle.

Suggestions

Merge "When to Activate", "When to Use", and "How It Works" into a single section (or drop the two summary sections), since each restates the description and the detailed sections; this alone would cut roughly a third of the body.

Add templates/context.example.md to the bundle or repoint the two references to the actual template location, since the dead link lands at the skill's key action — creating CONTEXT.md.

State the ADR-reuse boundary once (in the ADR Handoff section) and let "Related Skills" carry a one-line pointer instead of restating the rule in How It Works, Examples, Anti-Patterns, and Attribution.

DimensionReasoningScore

Conciseness

The prose itself is dense with no filler explanations of known concepts, but "When to Activate", "When to Use", and "How It Works" substantially restate each other and the earlier detailed sections, and the ADR-boundary rule is repeated roughly four times — the document could be tightened considerably. It is mostly efficient rather than noticeably padded, so it sits at the 'could be tightened' anchor rather than the one below.

3 / 5

Actionability

For an instruction-only skill the guidance is mostly executable: concrete paths (.governance/docs-map.json, CONTEXT.md), explicit approval gates, specific probes ("whether one customer can have multiple logins"), the `needs confirmation` marking convention, and worked ambiguity examples like the cancellation/account cases. The gap is that the referenced templates/context.example.md does not exist in the bundle, leaving the artifact-creation step without its promised template.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (reuse mapped glossary → refine language → route durable decisions to ADR skill → keep tasks in the tracker) with real checkpoints: explicit user approval before creating a new artifact, evidence cross-checks against code and contracts, and deferral to domain owners for unresolved meanings. Minor gaps — no explicit validate-and-recover loops — keep it below the top anchor; the destructive/batch cap does not apply since operations are documentation edits behind approval gates.

4 / 5

Progressive Disclosure

Section structure is good and references/source.md is a valid, clearly signaled one-level-deep link, but templates/context.example.md is cited twice ("propose the default CONTEXT.md from templates/context.example.md" and "the [context template](templates/context.example.md)") and does not exist in the bundle — a dead link exactly at the point where a reader would create the artifact. A broken referenced path is more than the 'minor organization gaps' of the next anchor up.

3 / 5

Total

14

/

20

Passed

Description

82%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 that explicitly states both what the skill does and four concrete trigger conditions, and that draws a clear boundary against the related ADR skill. Its only weaknesses are that it names just two capabilities and omits natural synonyms such as "glossary" or "terminology" from its triggers.

DimensionReasoningScore

Specificity

The description names the domain and exactly two concrete actions — "Govern stable domain context with a narrowly scoped CONTEXT.md" and "route hard-to-reverse decisions to ECC's existing architecture-decision-records skill" — which matches the '1-2 concrete actions, but not comprehensive' anchor rather than the 'several specific actions' anchor above it.

3 / 5

Completeness

Both halves are explicit: what ("Govern stable domain context with a narrowly scoped CONTEXT.md... route hard-to-reverse decisions to ECC's existing architecture-decision-records skill") and when ("Use when domain terms require repeated explanation, one term has multiple meanings, unclear language causes module-boundary mistakes, or domain semantics must remain separate from architecture decisions") — matching the anchor for clear what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Trigger conditions are natural and specific ("domain terms require repeated explanation, one term has multiple meanings, unclear language causes module-boundary mistakes"), giving good keyword coverage, but common user synonyms like "glossary" or "terminology" are missing, so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (stable domain language) with distinct triggers, and explicitly handing decisions off to the architecture-decision-records skill disambiguates its closest neighbor, minimizing conflict risk.

5 / 5

Total

17

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

affaan-m/ECC

Path

.agents/skills/context-and-decisions/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.