Roo Conflict Resolution
zgsm-ai/costrict
Provides comprehensive guidelines for resolving merge conflicts intelligently using git history and commit context.
Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they…
Install Validate Session Schemas
$ npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rajbos/ai-engineering-fluency validate-session-schemas --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/validate-session-schemas .claude/skills/validate-session-schemas && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "validate-session-schemas" agent skill from https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemas into .claude/skills/validate-session-schemas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validate-session-schemas", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemasType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rajbos/ai-engineering-fluency validate-session-schemas --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/validate-session-schemas .agents/skills/validate-session-schemas && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "validate-session-schemas" agent skill from https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemas into .agents/skills/validate-session-schemas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validate-session-schemas", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rajbos/ai-engineering-fluency validate-session-schemas --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/validate-session-schemas .cursor/skills/validate-session-schemas && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "validate-session-schemas" agent skill from https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemas into .cursor/skills/validate-session-schemas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validate-session-schemas", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rajbos/ai-engineering-fluency.git --path .claude/skills/validate-session-schemas--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rajbos/ai-engineering-fluency validate-session-schemas --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/validate-session-schemas .gemini/skills/validate-session-schemas && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "validate-session-schemas" agent skill from https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemas into .gemini/skills/validate-session-schemas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validate-session-schemas", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rajbos/ai-engineering-fluency validate-session-schemasInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/validate-session-schemas .github/skills/validate-session-schemas && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "validate-session-schemas" agent skill from https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemas into .github/skills/validate-session-schemas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validate-session-schemas", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rajbos/ai-engineering-fluency validate-session-schemas --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/validate-session-schemas .opencode/skills/validate-session-schemas && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "validate-session-schemas" agent skill from https://github.com/rajbos/ai-engineering-fluency/tree/main/.claude/skills/validate-session-schemas into .opencode/skills/validate-session-schemas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validate-session-schemas", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
validate-session-schemas- GitHub stars
- 116
- Token cost
- ~1.8k tokens
- SKILL.md length
- 692 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they…
- Works in 2 steps: Did anything break? — Drift detection… → Is there new information to use? — Any…
- Development work in your project
- SKILL.md covers Why this skill exists, Platforms covered, Usage and How drift and new-field…, plus 3 more sections
- Calls node
What it does
Validate Session Schemas is an agent skill from rajbos/ai-engineering-fluency. Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they still match the documented schema, while surfacing newly-discovered fields we could start using. Use after an editor/CLI update, when adding a parser, or on a schedule to catch schema drift early.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. It works with JetBrains IDEs and Visual Studio Code. The repository describes itself as: Extension that shows information about the estimated token usage and more of AI in editors/CLI's. The licence is MIT.
When your agent uses it
- Development work in your project
Example prompts
- “/validate-session-schemas”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Did anything break? — Drift detection against a small set of fields our
- Is there new information to use? — Any field observed on disk that is not
What it can do on your machine
Read from SKILL.md and the folder at commit 64b51e6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Validate Session Schemas loads about 1.8k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 692 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from rajbos/ai-engineering-fluency at commit 64b51e6, republished under its MIT licence (© rajbos). 692 words, ~1,824 tokens.
Download SKILL.mdSave it as
.claude/skills/validate-session-schemas/SKILL.md (or your agent's skills folder).- name
- validate-session-schemas
- description
- Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they still match the documented schema, while surfacing newly-discovered fields we could start using. Use after an editor/CLI update, when adding a parser, or on a schedule to catch schema drift early.
Validate Session Schemas Skill
Validates that recent session log files on the current machine still match the schema our parsers expect, per supported platform, and surfaces new fields that appeared on disk but aren't documented/used yet.
It answers two questions in one pass:
- Did anything break? — Drift detection against a small set of fields our
parsers actually depend on ("contracts"). A missing required field on an
observed record type is a
DRIFTfailure. - Is there new information to use? — Any field observed on disk that is not in the known baseline ("knownFields") is reported as a new field. These are candidates for new features or better token attribution (e.g. real token counts, new model metadata, new event types).
Why this skill exists
The pre-existing copilot-log-analysis skill (analyze-session-schema.ps1)
only covered VS Code Copilot Chat JSON + Copilot CLI JSONL + OpenCode, with
crude substring-based "new field" detection. It did not loop per supported
platform, had no recency window, and didn't cover JetBrains, Claude Code,
Gemini CLI, or Antigravity. This skill closes that gap.
Platforms covered
The source of truth for supported platforms is
src/adapters/adapterRegistry.ts. This skill validates the
file-based JSON/JSONL ecosystems that have schema docs under
docs/logFilesSchema/:
| Platform id | Editor / tool | Format | Discovery root |
|---|---|---|---|
copilot-chat | VS Code Copilot Chat | json / jsonl | VS Code variants workspaceStorage/*/chatSessions, globalStorage |
copilot-cli | Copilot CLI | jsonl | ~/.copilot/session-state/ |
jetbrains | JetBrains Copilot | jsonl | ~/.copilot/jb/{uuid}/partition-*.jsonl |
claude-code | Claude Code | jsonl | ~/.claude/projects/{hash}/*.jsonl |
gemini-cli | Gemini CLI | jsonl | ~/.gemini/tmp/*/chats/session-*.jsonl |
antigravity | Antigravity | jsonl | ~/.gemini/antigravity/brain/*/.system_generated/logs/transcript.jsonl |
opencode | OpenCode | json / jsonl | <xdg-data>/opencode/storage/session/**/ses_*.json; also opencode.db (SQLite, via node:sqlite) |
Not validated by this skill (DB / binary formats that need the adapters'
own parsers, so a generic JSON walker can't read them): crush (SQLite),
visual-studio (MessagePack), continue, mistral-vibe, claude-desktop.
They are listed in the report under "Not validated" so coverage is never
silently overstated. If you add a new file-based adapter, add a discovery
function + a schema-baselines.json entry here too.
Usage
# Validate every platform's recent sessions (last 30 days, 5 files each)
node .github/skills/validate-session-schemas/validate-session-schemas.js
# Widen the window and look at more files
node .github/skills/validate-session-schemas/validate-session-schemas.js --days 60 --max 10
# One platform only
node .github/skills/validate-session-schemas/validate-session-schemas.js --platform claude-code
# Machine-readable output (for CI / further processing)
node .github/skills/validate-session-schemas/validate-session-schemas.js --json
# Refresh the "known fields" snapshot from what's on disk (does NOT touch contracts)
node .github/skills/validate-session-schemas/validate-session-schemas.js --update-baseline
# Include truncated example values (may contain user content — off by default)
node .github/skills/validate-session-schemas/validate-session-schemas.js --include-examplesOptions
| Flag | Meaning |
|---|---|
--days N | Only consider files modified within the last N days (default 30; 0 = no limit) |
--max N | Analyze at most N most-recent files per platform (default 5) |
--platform <id> | Validate a single platform |
--update-baseline | Rewrite knownFields from observed fields; never modifies contracts |
--include-examples | Capture truncated example values per field |
--fail-on-new-fields | Exit non-zero when new fields are discovered |
--json | Emit JSON only |
--help | Usage |
Exit codes
0— all observed contracts pass (new fields alone do not fail unless--fail-on-new-fields)1— contract drift or an unparseable file2— configuration / environment error (bad args, missing baseline)
Show full SKILL.md (285 more words)Show less
Per-platform statuses
PASS, DRIFT, NO_FILES (editor not installed / no sessions),
NO_RECENT_FILES (sessions exist but none in the window), INCONCLUSIVE
(recent files existed but no parseable records).
How drift and new-field detection work
schema-baselines.json holds two independent things per platform:
contracts— hand-maintained list of the fields our parsers depend on, optionally scoped byformat(json/jsonl) and adiscriminator(the JSONL eventtype/kind). A contract is only evaluated when matching records are actually observed, so a union format never produces false drift for an event type that simply wasn't present.--update-baselinenever changes contracts — edit them by hand when the parser's real dependencies change.knownFields— the last-known set of observed field paths. New = observed − known. Refresh with--update-baselineonce you've reviewed and accepted the new fields.
Field-path notation: a.b nested, arr[] array items, arr[].c a field inside
array items.
Acting on results
- DRIFT → a required field disappeared. Open the platform's doc under
docs/logFilesSchema/and the matching adapter undersrc/adapters/, confirm the change, and update both the parser and the contract. - New fields → review them. If useful (e.g. real token counts, new model
metadata, a new event type), document them in
docs/logFilesSchema/, consider wiring them into the adapter/parser, then run--update-baselineto clear them from future reports.
Periodic run (optional)
This script is dependency-free Node and CI-friendly via its exit codes:
- name: Validate recent session schemas
run: node .github/skills/validate-session-schemas/validate-session-schemas.js --json(On CI the runner usually has no local session files, so most platforms report
NO_FILES and the job passes — it's most useful run on a developer machine or a
self-hosted runner that has real session data.)
Related
docs/logFilesSchema/— per-platform schema documentation (the human source of truth).github/skills/copilot-log-analysis/— deeper Copilot-only schema field dump (analyze-session-schema.ps1).github/skills/validate-app-db-schema/— validates the unrelated~/.copilot/data.dbhierarchy schemasrc/adapters/adapterRegistry.ts— canonical list of supported ecosystems
© rajbos, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/validate-session-schemas of rajbos/ai-engineering-fluency.
Open the folder on GitHubat commit 64b51e6
Compare with similar skills
Validate Session Schemas next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Validate Session Schemas this skillrajbos/ai-engineering-fluency | 116 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Roo Conflict Resolutionzgsm-ai/costrict | 4.4k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Evals Contextzgsm-ai/costrict | 4.4k | 1 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Debug Surefireeclipse-rdf4j/rdf4j | 420 | — | ~2.4k | Automated safety check: Pass | BSD-3-Clause | |
| Claude Docs Consultantcentminmod/my-claude-code-setup | 2.7k | — | ~959 | Automated safety check: Pass | MIT | |
| Doc SyncJetBrains/ideavim | 10k | 2 repos | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Evals Context
zgsm-ai/costrict
Provides context about the CoStrict evals system structure in this monorepo.
Debug Surefire
eclipse-rdf4j/rdf4j
Debug Maven Surefire unit tests by running them in JDWP "wait for debugger" mode (-Dmaven.surefire.debug) and attaching to the forked test JVM using jdb (preferred for CLI/agent debugging)…
Claude Docs Consultant
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
- Official
Doc Sync
JetBrains/ideavim
Keeps IdeaVim documentation in sync with code changes. An agent skill from JetBrains/ideavim.
- Official
Changelog
JetBrains/ideavim
Maintains the IdeaVim changelog (CHANGES.md). An agent skill from JetBrains/ideavim.
More from rajbos/ai-engineering-fluency
All 21 skills in this repoCheck Urls
rajbos/ai-engineering-fluency
Find all hardcoded URLs in TypeScript source files and verify they resolve (return HTTP 2xx/3xx).
Create Issue
rajbos/ai-engineering-fluency
Create a well-scoped GitHub issue in this repo. An agent skill from rajbos/ai-engineering-fluency.
Deduplicate Code
rajbos/ai-engineering-fluency
Detect copy-pasted code blocks across the shared source (vscode-extension/src, the repo-root src/, cli/src) with the dependency-free check-code-duplication.js detector, then pick one duplicate group…
Improve Tool Families
rajbos/ai-engineering-fluency
Analyze coverage of the vscode-extension's tool-family definitions (DEFAULTTOOLFAMILIES in vscode-extension/src/toolFamilies.ts) against the canonical tool-name list in src/toolNames.json and/or a…
Load Cache Data
rajbos/ai-engineering-fluency
Load and display the last 10 cache entries as raw JSON output.
PR Risk Review
rajbos/ai-engineering-fluency
Assess the risk of a changeset (a PR, a branch, or the working tree) and classify it as low, medium, or high with a written rationale.
Related
Works with
Categories
Questions about Validate Session Schemas
What does Validate Session Schemas do?
Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they…. Validate Session Schemas is an agent skill from rajbos/ai-engineering-fluency. Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they still match the documented schema, while surfacing newly-discovered fields we could start using.
When should I use Validate Session Schemas?
Validate Session Schemas fits situations like: development work in your project.
How do I install Validate Session Schemas in Claude Code?
Run `npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a claude-code`. Or copy the skill folder (.claude/skills/validate-session-schemas in rajbos/ai-engineering-fluency) into .claude/skills/validate-session-schemas in your project. Claude Code loads it when a task matches its description.
How do I install Validate Session Schemas in Codex?
Run `npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a codex`. Or copy the skill folder (.claude/skills/validate-session-schemas in rajbos/ai-engineering-fluency) into .agents/skills/validate-session-schemas in your project. Codex loads it when a task matches its description.
Can I use Validate Session Schemas in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rajbos/ai-engineering-fluency --skill validate-session-schemas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/validate-session-schemas, .gemini/skills/validate-session-schemas, .github/skills/validate-session-schemas and .opencode/skills/validate-session-schemas in your project.
What does Validate Session Schemas need to run?
Going by SKILL.md and its folder, Validate Session Schemas needs the command-line tools its instructions call (node).
Does Validate Session Schemas access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Validate Session Schemas safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Validate Session Schemas use?
Validate Session Schemas is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Validate Session Schemas use?
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Validate Session Schemas?
Skills that share tags, products or a category with Validate Session Schemas: Roo Conflict Resolution (zgsm-ai/costrict, 4.4k stars), Evals Context (zgsm-ai/costrict, 4.4k stars), Debug Surefire (eclipse-rdf4j/rdf4j, 420 stars) and Claude Docs Consultant (centminmod/my-claude-code-setup, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Validate Session Schemas?
rajbos (a GitHub user) maintains it in rajbos/ai-engineering-fluency, which has 116 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 8, 2026.
Source: rajbos/ai-engineering-fluency on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.