grounding

Establish what is actually true and current for the surface you are about to change — not just search. Grounding = locate the authoritative source and reconcile sources that disagree (code vs doc, migration vs schema, memory vs current code, live vs archived), not take the first hit. Use before any grep/find/explore of the codebase or docs, when deciding which of several definitions is the real one, or when a doc or memory conflicts with the code. Covers the source-of-truth hierarchy, reconciliation discipline, scoped ripgrep, and the docs/tags.yml + docsearch.py index.

Quality

85%

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

Quality

Content

86%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 is an efficient, actionable grounding reference: concrete scoped-ripgrep and docsearch commands, a clear per-surface authority table, and well-signaled one-level-deep references. The only soft spot is a mildly redundant opening paragraph and a decision-flow (vs. validate-loop) structure.

Dimension	Reasoning	Score
Conciseness	Dense and Grida-specific, assuming Claude's competence (no explanations of ripgrep/git), but the opening paragraph rephrases the frontmatter description and could be trimmed.	4 / 5
Actionability	Copy-paste ready commands throughout — 'rg PATTERN editor/grida-canvas packages', 'rg PATTERN -g ''!/docs/_history/'', and 'uv run $S tags / find / show' — cover the common grounding cases with exact syntax.	5 / 5
Workflow Clarity	The decision procedure is clear (name the surface → trust the authoritative source → reconcile disagreements with 'git log -1 recency, what the running entrypoint imports, what tests assert' → 'surface a material conflict to the user') but it is a decision flow rather than a validate-fix-retry loop.	4 / 5
Progressive Disclosure	Well-organized sections (Source of truth, Dead-tree traps, Grounding the docs, Related skills) with a single one-level-deep bundle reference to scripts/docsearch.py (verified present), keeping the overview navigable and detail pushed to the script.	5 / 5
	Total	18 / 20 Passed

Description

83%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 is strong: it states concrete capabilities, gives explicit 'use when' trigger conditions, and carves out a distinct grounding niche. Minor gaps in action coverage and overlap with related skills prevent a perfect score.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'locate the authoritative source and reconcile sources that disagree', 'scoped ripgrep', and 'docs/tags.yml + docsearch.py index' — with only minor coverage gaps around the reconciliation procedure itself.	4 / 5
Completeness	Explicitly answers both what ('Covers the source-of-truth hierarchy, reconciliation discipline, scoped ripgrep, and the docs/tags.yml + docsearch.py index') and when ('Use before any grep/find/explore... when a doc or memory conflicts with the code') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases appear ('grep/find/explore of the codebase', 'when a doc or memory conflicts with the code', 'deciding which of several definitions is the real one'); a few common synonyms are absent but coverage is good.	4 / 5
Distinctiveness Conflict Risk	A clear niche (source-of-truth reconciliation) with distinct triggers, but acknowledged overlap with the related database/research/naming skills keeps it just below a 5.	4 / 5
	Total	17 / 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: gridaco/grida
Path: .agents/skills/grounding/SKILL.md
Commit: 8ef5e53

Reviewed: about 11 hours ago

Table of Contents

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.