CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

realize

This skill should be used when the user asks to "run the eval", "test whether the protocol actually works at runtime", "check type realization", "measure protocol fulfillment", "run the type-realization suite", "does the gate actually stop", or wants runtime evidence that a protocol's formal transition contract is realized rather than an assessment of downstream artifact quality. Invoke explicitly with /realize and a skill argument.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/realize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, expert-oriented instruction skill with genuinely executable workflow commands and present validation checkpoints for a batch operation. Its weakness is token efficiency: substantial design rationale and a report-reading section duplicate what the runbook reference carries, and a few referenced paths (evals/, harness.config.json) do not resolve within the bundle.

Suggestions

Trim the "Reading results" section to the integrity-first rule and the definition of pass_k, and delegate the per-target manual-observation enumerations (inquire/grasp/conduct lists) to references/runbook.md, which already claims to cover how to read the report.

Introduce the `report` command concretely in the Workflow block (how it is invoked and where its output lands) instead of only referencing it in the failure-mode sentence.

Move design rationale that is not needed at run time — the sham-arm literature justification and the credential-rotation/symlink explanation — into references/runbook.md or references/grader-design.md, keeping only the operational rule in the body.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes Claude's competence (no basic-concept explanations), but it carries notable duplication and over-long rationale: the multi-paragraph "Reading results" section inlines detail that the body itself says "references/runbook.md" carries, and passages like the credential-rotation and sham-arm justifications read as design documentation rather than operational instruction. Mostly efficient with sections that should be tightened or moved matches anchor 3; it avoids 2 because nothing is beginner-level padding, and misses 4 because the duplicated report-reading and rationale material is a real trimming opportunity.

3 / 5

Actionability

The Workflow section gives a copy-paste bash block (cd into scripts, setup.sh/run.sh/teardown.sh with REALIZE_RUNNER variants and env vars) and names concrete config keys (harness.config.json, REALIZE_ARMS, targets registry). Minor gaps keep it from 5: the `report` command is referenced ("makes `run` or `report` exit non-zero") but never introduced, and generating/viewing the report is never concretely shown.

4 / 5

Workflow Clarity

The run sequence is clearly ordered (setup → run → teardown, with runner and arm variants), and validation is present despite the batch nature of the matrix: "Read `integrity` first", non-zero exits on "a launch failure, missing cell, unreadable predicate, or treatment-integrity failure ... while preserving partial transcripts", and explicit guidance that low-integrity rows are not evidence. It is not 5 because prerequisites (read the runbook first, install the ink-figure marketplace) are scattered across prose rather than presented as an ordered checklist with error-recovery loops.

4 / 5

Progressive Disclosure

Sections are well organized and the core references — references/runbook.md, references/grader-design.md, scripts/harness.mjs — exist in the bundle, are one level deep, and are clearly signaled both inline and in an annotated "Additional Resources" list. Minor gaps: the body references `evals/*.sh` and `harness.config.json`, which are not present in this bundle, and the long per-target report-reading enumerations are inlined where the runbook reference already covers them. Good structure with minor organization gaps matches anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

77%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 with excellent, natural trigger-term coverage and a clearly bounded niche. Its main weakness is an indirect statement of what the skill actually does — the capability is framed as what the user wants rather than enumerated actions — leaving a reader to infer the mechanics from the body.

DimensionReasoningScore

Specificity

The description states one concrete capability — "wants runtime evidence that a protocol's formal transition contract is realized" — but never enumerates the skill's actual actions (driving the model matrix, capturing the JSONL trace, grading predicates). It names the domain with 1-2 concrete actions, matching anchor 3; it is not 4 because no list of specific operations is given, and not 2 because the what is stated rather than purely generic.

3 / 5

Completeness

The "when" is explicit and rich (a full quoted trigger list plus invocation guidance "Invoke explicitly with /realize and a skill argument"), and the "what" is present via "runtime evidence that a protocol's formal transition contract is realized rather than an assessment of downstream artifact quality". It falls short of anchor 5 because the what is stated indirectly as what the user wants rather than as what the skill does, and it exceeds anchor 3 because the when is fully explicit.

4 / 5

Trigger Term Quality

Six quoted natural phrasings — "run the eval", "test whether the protocol actually works at runtime", "check type realization", "measure protocol fulfillment", "run the type-realization suite", "does the gate actually stop" — cover the synonym space a user of this domain would naturally say. Comprehensive coverage including colloquial variants ("does the gate actually stop") matches anchor 5.

5 / 5

Distinctiveness Conflict Risk

Niche jargon ("type realization", "formal transition contract") and an explicit boundary against artifact-quality assessment give it a clear niche with minimal conflict risk, but the trigger "run the eval" is generic and could overlap with other eval-runner skills in a repo with multiple evals. Mostly distinct with minor overlap risk matches anchor 4 rather than 5.

4 / 5

Total

16

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

jongwony/epistemic-protocols

Path

.claude/skills/realize/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.