input-grounding
Ground a Stage's work in supplied Artifacts, source material, and explicit confirmations while separating model inference.
Skill by ole3021
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ole3021-input-grounding
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/input-grounding
What's inside
- Skill name
input-grounding- Description
- Ground a Stage's work in supplied Artifacts, source material, and explicit confirmations while separating model inference. Use before authoring or reviewing any Stage Artifact.
- License
- unknown
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ole3021/intent-loom
- 0.514score
domain-language-discovery
ole3021
Discover and preserve a product's shared business language, rules, events, and boundary clues from grounded Artifacts.
SkillBFreshness: BClaude Code +9 - 0.514score
outcome-criteria-design
ole3021
Design observable, implementation-independent criteria that show whether a declared outcome, rule, or constraint has been met.
SkillBFreshness: BClaude Code +9 - 0.514score
boundary-decomposition
ole3021
Decompose a grounded goal into cohesive, traceable units appropriate to the current Stage Artifact.
SkillBFreshness: BClaude Code +9 - 0.511score
claim-evidence-alignment-review
ole3021
Independently check whether criteria, evidence, and source references actually support the claims they are linked to.
SkillBFreshness: BClaude Code +9 - 0.511score
semantic-review
ole3021
Independently review a Stage Artifact for ambiguity, contradiction, missing boundaries, unsupported meaning, and weak verifiability.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 31, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ole3021/intent-loom
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ole3021
- 0.514score
domain-language-discovery
ole3021
Discover and preserve a product's shared business language, rules, events, and boundary clues from grounded Artifacts.
SkillBFreshness: BClaude Code +9 - 0.514score
outcome-criteria-design
ole3021
Design observable, implementation-independent criteria that show whether a declared outcome, rule, or constraint has been met.
SkillBFreshness: BClaude Code +9 - 0.514score
boundary-decomposition
ole3021
Decompose a grounded goal into cohesive, traceable units appropriate to the current Stage Artifact.
SkillBFreshness: BClaude Code +9 - 0.511score
claim-evidence-alignment-review
ole3021
Independently check whether criteria, evidence, and source references actually support the claims they are linked to.
SkillBFreshness: BClaude Code +9 - 0.511score
semantic-review
ole3021
Independently review a Stage Artifact for ambiguity, contradiction, missing boundaries, unsupported meaning, and weak verifiability.
SkillBFreshness: BClaude Code +9
Cite this page
input-grounding skill. Agent Mart. https://agentmart.dev/skills/ole3021-input-grounding (last updated 2026-10-24)