semantic-snapshot
Review the recent conversation for settled terminology and decisions, then update semantic files and missing ADRs.
Skill by ElmoJones3
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/elmojones3-semantic-snapshot
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
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/semantic-snapshot
What's inside
- Skill name
semantic-snapshot- Description
- Review the recent conversation for settled terminology and decisions, then update semantic files and missing ADRs. Use only when explicitly requested.
- License
- MIT
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- adr-format.md · references/
SKILL.md (first lines)
# Capture a semantic snapshot Retrace the relevant part of the conversation and reconcile what was settled with the repository. Write clear conclusions. Surface uncertain candidates instead of guessing. This is a recording pass, not another design session. Do not reopen settled work, start a new interview, or turn the conversation into a specification. ## Load the rules Load `semantic-mapping` before reviewing terminology. Report a missing skill and do not recreate its semantic rules from memory. Read [references/adr-format.md](references/adr-format.md) before classifying decision points or creating or superseding an ADR. ## Set the scope - Use the topic, decision, or conversation segment named by the user. - Otherwise use the coherent segment leading to this invocation, stopping where the subject changes. - Include relevant repository changes and existing semantic files or ADRs when they confirm what the conversation settled. - Use a compacted thread summary only for conclusions it marks as explicitly accepted. If the requested segment or its rationale is unavailable, state what is missing instead of reconstructing it from unrelated files. ## Collect the conclusions Separate the segment into: - settled terms, definitions, rejected synonyms, and owners; - clearly settled decisions with their context and reason; and - unresolved semantic conflicts or possible decisions whose meaning, choice, reason, scope, or acceptance remains unclear. An assistant recommendation or implementation choice is not settled until the user explicitly chooses or accepts it. Completed work may confirm an accepted decision; it cannot establish acceptance. ## Reconcile the repository 1. Compare the collected terms with the relevant semantic files and map. Apply `semantic-mapping` to add, correct, move, or remove entries. 2. Compare clearly settled decisions with `docs/adr/`. Write missing ADRs and supersede contradicted ADRs. Do not duplicate a decision that is already recorded. 3. Leave unresolved items unwritten. Report each candidate with the exact point that remains unsettled. 4. Inspect the diff for invented language, behavior copied into semantics, duplicated definitions, and ADRs that record recommendations rather than decisions. Do not edit unrelated documentation, implementation, or tests during a snapshot. ## Report the snapshot Account for every collected item as already recorded, written now, or reported as unresolved. Name the semantic files and ADRs created or changed. Then list unresolved semantic conflicts and ADR candidates with the exact point that remains unsettled. Do not pad the report with terms and decisions that were already recorded correctly. If every item was already recorded and no candidate remains, state that no changes were needed.
From ElmoJones3/opinionated, MIT.
More from ElmoJones3/opinionated
- 0.592score
domain-modeling
ElmoJones3
Make business objects own their behavior, construction, invariants, and consequences.
SkillAFreshness: A★ 1Claude Code +9 - 0.549score
principle-bound-telemetry
ElmoJones3
Bound collection cost and protect business outcomes when configuring or reviewing telemetry fields, cardinality, queues, exporters, sampling, loss reporting…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-interpret-observations
ElmoJones3
Preserve evidence meaning when receiving observations, selecting current execution evidence, or calculating operational reports, rates, and coverage.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-always-comment-code
ElmoJones3
Preserve the reason code exists beside every source file, named declaration, and member.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-code-first-documentation
ElmoJones3
Treat generated OpenAPI and its documentation UI as part of every HTTP boundary.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-observe-operations
ElmoJones3
Establish operation ownership and one coherent completion observation when adding or reviewing instrumentation across logs, traces, or metrics.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-observe-progress
ElmoJones3
Define useful advancement, legitimate waits, and fresh live evidence when instrumenting or reviewing streams, long-running operations, or stall and spin…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-prefer-pure-functional-patterns
ElmoJones3
Prefer pure calculations and explicit effects when creating, changing, reviewing, or diagnosing transformations, validators, reducers, pipelines, or state…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
mind-merge
ElmoJones3
Adjudicate long or branching design conversations by maintaining a local graph of open Questions, accepted Decisions, Evidence, dependencies, provenance, and…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
semantic-mapping
ElmoJones3
Keep project terms and definitions consistent in SEMANTICS.md and SEMANTIC-MAP.md.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
principle-sql-preserve-query-cardinality
ElmoJones3
Preserve root selection, child completeness, ordering and bounded query work when implementing or reviewing SQL aggregate reads, filters, joins or pagination.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
stay-in-your-lane
ElmoJones3
Keep agents inside user-defined scope and authority.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 21, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ElmoJones3/opinionated
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ElmoJones3
- 0.592score
domain-modeling
ElmoJones3
Make business objects own their behavior, construction, invariants, and consequences.
SkillAFreshness: A★ 1Claude Code +9 - 0.549score
principle-observe-progress
ElmoJones3
Define useful advancement, legitimate waits, and fresh live evidence when instrumenting or reviewing streams, long-running operations, or stall and spin…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-always-comment-code
ElmoJones3
Preserve the reason code exists beside every source file, named declaration, and member.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-code-first-documentation
ElmoJones3
Treat generated OpenAPI and its documentation UI as part of every HTTP boundary.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-observe-operations
ElmoJones3
Establish operation ownership and one coherent completion observation when adding or reviewing instrumentation across logs, traces, or metrics.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
principle-prefer-pure-functional-patterns
ElmoJones3
Prefer pure calculations and explicit effects when creating, changing, reviewing, or diagnosing transformations, validators, reducers, pipelines, or state…
SkillBFreshness: B★ 1Claude Code +9
Cite this page
semantic-snapshot skill. Agent Mart. https://agentmart.dev/skills/elmojones3-semantic-snapshot (last updated 2026-10-24)