Tessl • The management layer for AI agent skills

SkillPublic

causal

Analyze cause-and-effect relationships in the Semantica knowledge graph — causal chains, interventions, counterfactuals, and causal influence scores.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/causal/SKILL.md

Quality

Content

72%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 tight, well-organized command reference with excellent token efficiency and clean per-subcommand structure. Its weaknesses are incomplete code (undefined variables) and implicit, sometimes inconsistent argument-to-API mapping across the three subcommands.

Suggestions

Make the code executable: show how ctx, decision_id, and depth are obtained (e.g., building AgentContext and parsing $ARGUMENTS into the variables used in the API calls).

Fix or explain the argument mapping: reconcile '--subject <node>' and 'counterfactual <fact>' with 'decision_id', and either use '--scenario <json>' in the intervene code or drop the flag.

Add a brief example invocation and sample output for one subcommand so the expected result format (e.g., 'chain steps, cause strength, effect reach') is concrete.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference: one-line descriptions, minimal code blocks, and zero explanation of concepts Claude already knows — every token earns its place, matching the anchor-5 example of lean, competence-assuming content.	5 / 5
Actionability	The code blocks call concrete APIs (CausalChainAnalyzer, get_causal_chain, find_root_causes) but are not executable as written: 'ctx', 'decision_id', and 'depth' are never constructed or bound from arguments, and the AgentContext import goes unused — key details are missing rather than minor gaps.	3 / 5
Workflow Clarity	Three subcommand sections are present and sequenced per command, but the mapping from CLI arguments to code variables is implicit or inconsistent: '--subject <node>' becomes 'decision_id', 'counterfactual <fact>' becomes 'decision_id', and '--scenario <json>' never appears in the intervene code.	3 / 5
Progressive Disclosure	The skill is short (~70 lines), has no bundle files, and needs none: content is cleanly split into per-subcommand sections with no inline material that belongs in separate reference files, which per the simple-skill exception merits a 5.	5 / 5
	Total	16 / 20 Passed

Description

70%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 concise, well-scoped description with good domain-specific trigger terms and a clear 'what', anchored firmly in the Semantica niche. Its main weakness is the absence of any 'when to use' guidance, which caps completeness and slightly limits trigger discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about root causes, causal impact, interventions, or counterfactuals in the Semantica graph.'

Include natural trigger variations users might say, such as 'root cause analysis', 'impact analysis', or 'what-if', to broaden trigger-term coverage.

Enumerate the concrete actions per capability (e.g., 'build causal chains, score decision impact, trace root causes, replay causal history at a point in time') to reach comprehensive specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Semantica knowledge graph') and lists several specific capability areas — 'causal chains, interventions, counterfactuals, and causal influence scores' — but subsumes them under a single verb without enumerating the concrete actions each entails, so it falls just short of the comprehensive anchor 5.	4 / 5
Completeness	The 'what' is clearly stated ('Analyze cause-and-effect relationships... causal influence scores'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Natural causal-analysis terms like 'cause-and-effect', 'causal chains', 'interventions', and 'counterfactuals' are present and would be said by users needing this skill, but common variations such as 'root cause analysis', 'impact analysis', or Semantica-specific trigger phrases are missing, keeping it below anchor 5.	4 / 5
Distinctiveness Conflict Risk	Scoping to 'the Semantica knowledge graph' gives the skill a clear niche with distinct triggers; generic causal-analysis requests outside Semantica would not plausibly mis-trigger it, matching the minimal-conflict anchor 5.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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: semantica-agi/semantica
Path: plugins/skills/causal/SKILL.md
Revision: 981a915

Reviewed: 28 days ago

Discovery Implementation Validation

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.

causal

Table of Contents

Is this your skill?