CtrlK
BlogDocsLog inGet started
Tessl Logo

goal-research

Delegate factual research to a Codex CLI session that uses Codex's builtin `goal` command and invokes Aitesis (`$inquire`) for Tavily-based external verification. User-invoked via /goal-research.

62

Quality

73%

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 ./epistemic-cooperative/skills/goal-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is a tightly written, highly executable delegation workflow with strong validation and error-recovery checkpoints. Its main limitation is that all detail lives in one file with no progressive disclosure via references, though the organization is clear.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, explaining only load-bearing gotchas (the dotted config-override replacement, the `grep '^{'` jq-abort trap); minor prose like 'Why this composition' could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands with concrete flags (`codex exec --ephemeral --json --color never ...`, `grep '^{' ... | jq -rs ...`), real temp-file paths, and a complete prompt template covering the common case.

5 / 5

Workflow Clarity

Phases 1–4 are explicitly sequenced with validation checkpoints (binary check, tool-call count check for unverified answers, empty-extraction crash detection, warn-file grep) and error-recovery feedback loops.

5 / 5

Progressive Disclosure

A single self-contained file, well-organized into Architecture and Phases 1–4 with no nested references; some detailed error-handling prose could be split into a reference, but structure is solid.

4 / 5

Total

18

/

20

Passed

Description

58%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 conveys concrete capabilities and a distinct tooling niche, but is weighed down by internal tool jargon and lacks an explicit 'Use when…' trigger clause. It is functional but not optimized for natural user invocation.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to delegate fact-finding or external source verification to a background research session.'

Surface natural user phrases ('research', 'fact-check', 'verify sources', 'look up') ahead of internal tool names so the description reads as user-facing.

Lead with the outcome ('Delegates factual research and source verification') and relegate Codex/Aitesis/Tavily mechanics to a secondary clause to reduce jargon load.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Delegate factual research', 'uses Codex's builtin `goal` command', 'invokes Aitesis (`$inquire`) for Tavily-based external verification' — with only minor coverage gaps.

4 / 5

Completeness

The 'what' is clear, but the 'when' is only weakly implied by 'User-invoked via /goal-research' with no explicit 'Use when…' trigger clause, which caps completeness at 3 per the guidelines.

3 / 5

Trigger Term Quality

Contains some natural terms ('factual research', 'external verification') but is dominated by internal tool names (Aitesis, `$inquire`, Tavily) users would not say, and misses common synonyms like 'fact-check' or 'look up'.

3 / 5

Distinctiveness Conflict Risk

The Codex/Aitesis/Tavily tooling and slash-command invocation form a distinct niche, but 'factual research / external verification' overlaps with closely related research skills.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jongwony/epistemic-protocols
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.