CtrlK
BlogDocsLog inGet started
Tessl Logo

context-discovery

Use when coding standards, security patterns, or project conventions need to be discovered before implementation begins.

62

Quality

75%

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/claude-code/skills/context-discovery/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable with a clear, gated workflow and good error recovery, but it carries some motivational padding and points to a protocol file that is not bundled.

Suggestions

Either add the referenced context-discovery-protocol.md to ./references/ or remove the link and inline the essential protocol details, since the referenced file does not exist.

Trim the "Remember" and "Announce at start" boilerplate to lean instructional content that assumes Claude's competence.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the "Remember" section (e.g. "Training data is outdated—context is current", "Context FIRST, code SECOND"), the "Announce at start" line, and the "Related" list add motivational/boilerplate tokens that could be trimmed.

2 / 3

Actionability

Provides concrete executable commands ("/context-discovery [what you're implementing]", "/install-context"), specific file-path templates, and a copy-paste-ready delegation example rather than vague direction or pseudocode.

3 / 3

Workflow Clarity

Five clearly sequenced steps with an explicit gate (Critical files are "mandatory—proceed only after loading") and a prioritized Critical→High→Medium order, plus an error-handling section with recovery guidance.

3 / 3

Progressive Disclosure

Sections are reasonably organized, but the body references [OAC Context Discovery Protocol](./context-discovery-protocol.md) which is not present in any bundle directory — a broken one-level reference that undermines navigation.

2 / 3

Total

10

/

12

Passed

Description

72%

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 strong, explicit trigger guidance and a clear niche, but it never states the skill's action in active voice, leaving the "what" implied rather than explicit.

Suggestions

Lead with an active capability statement, e.g. "Discovers and ranks project coding standards, security patterns, and conventions relevant to a task," then keep the "Use when ... before implementation begins" trigger.

Add a couple of concrete actions (resolve the context root, rank files by priority) so specificity reaches the multi-action anchor.

DimensionReasoningScore

Specificity

Names the domain ("coding standards, security patterns, or project conventions") and an action ("need to be discovered"), but states only one soft action in passive voice rather than listing multiple concrete capabilities.

2 / 3

Completeness

The "when" is explicit ("Use when ... before implementation begins"), but the "what" is only implied via the trigger clause — there is no active statement of what the skill does (e.g., "Discovers and ranks ...").

2 / 3

Trigger Term Quality

"coding standards, security patterns, or project conventions" and "before implementation begins" are natural phrases a developer would actually say when requesting this kind of discovery.

3 / 3

Distinctiveness Conflict Risk

The pre-implementation context-discovery niche with explicit "before implementation begins" framing is distinct and unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
darrenhinde/OpenAgentsControl
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.