Weekly Engineering Retro
garrytan/gstack
Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.
Detect friction signals; graduate patterns into rules. An agent skill from athola/claude-night-market.
Install Friction Detector
$ npx skills add athola/claude-night-market --skill friction-detector -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install athola/claude-night-market friction-detector --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/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/abstract/skills/friction-detector .claude/skills/friction-detector && 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 "friction-detector" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detector into .claude/skills/friction-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "friction-detector", 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/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detectorType 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 athola/claude-night-market --skill friction-detector -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install athola/claude-night-market friction-detector --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/abstract/skills/friction-detector .agents/skills/friction-detector && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "friction-detector" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detector into .agents/skills/friction-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "friction-detector", 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 athola/claude-night-market --skill friction-detector -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install athola/claude-night-market friction-detector --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/abstract/skills/friction-detector .cursor/skills/friction-detector && 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 "friction-detector" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detector into .cursor/skills/friction-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "friction-detector", 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/athola/claude-night-market.git --path plugins/abstract/skills/friction-detector--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 athola/claude-night-market --skill friction-detector -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install athola/claude-night-market friction-detector --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/abstract/skills/friction-detector .gemini/skills/friction-detector && 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 "friction-detector" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detector into .gemini/skills/friction-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "friction-detector", 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 athola/claude-night-market friction-detectorInstalls 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 athola/claude-night-market --skill friction-detector -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/abstract/skills/friction-detector .github/skills/friction-detector && 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 "friction-detector" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detector into .github/skills/friction-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "friction-detector", 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 athola/claude-night-market --skill friction-detector -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install athola/claude-night-market friction-detector --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/abstract/skills/friction-detector .opencode/skills/friction-detector && 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 "friction-detector" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/friction-detector into .opencode/skills/friction-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "friction-detector", 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
friction-detector- GitHub stars
- 341
- Token cost
- ~1.8k tokens
- SKILL.md length
- 525 words
- Files
- 1
- Skills in repo
- 154
- Repo updated
- First seen
- Licence
- MIT
At a glance
Detect friction signals; graduate patterns into rules. An agent skill from athola/claude-night-market.
- Works in 5 steps: Scan Session for Signals → Compare Against Existing Log → Calculate Graduation Score → …
- Session retrospectives
- SKILL.md covers Overview, Friction Signal Types, Three-Tier Storage Graduation and Detection Workflow, plus 6 more sections
- Calls rg
What it does
Friction Detector is an agent skill from athola/claude-night-market. Detect friction signals; graduate patterns into rules. Use for session retrospectives.
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 Product & Project Management, covering Retrospectives. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.
When your agent uses it
- Session retrospectives
- Tasks that involve Retrospectives
Example prompts
- “/friction-detector”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 9f3eb00. 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:
rg
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
Friction Detector loads about 1.8k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 525 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 athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 525 words, ~1,789 tokens.
Download SKILL.mdSave it as
.claude/skills/friction-detector/SKILL.md (or your agent's skills folder).- name
- friction-detector
- description
- Detect friction signals; graduate patterns into rules. Use for session retrospectives.
- category
- workflow-optimization
- alwaysApply
- false
- trigger
- friction, friction detection, session retrospective, learning pipeline, recurring mistakes, pattern graduation, friction report
- model_hint
- standard
Friction-to-Learning Pipeline
Overview
Detect friction signals during agent execution, track them across sessions, and graduate recurring patterns into permanent guidance. Bridges the gap between ephemeral session friction and durable CLAUDE.md rules.
Research backing: Claude Coach (hook-based friction detection with SQLite storage), alirezarezvani's self-improving-agent (three-tier MEMORY to CLAUDE.md graduation), and the ACE framework (arXiv: evolving playbooks from execution feedback, +10.6% on agent tasks).
Current gap: LEARNINGS.md exists but requires manual aggregation via
/abstract:aggregate-logs. This skill adds automatic friction detection and
a structured promotion path.
Friction Signal Types
| Signal | Detection Method | Weight |
|---|---|---|
| Repeated corrections | User overrides same tool call 2+ times in session | High |
| Command failures | Exit code != 0 patterns (same command type fails repeatedly) | Medium |
| Permission denials | User denies tool call, indicating unexpected behavior | High |
| Re-reads | Same file read 3+ times in session (lost context) | Low |
| Retry loops | Same action attempted 3+ times with variations | Medium |
| User frustration | Explicit negative feedback or correction language | High |
Weight scoring: High = 3, Medium = 2, Low = 1 points per occurrence. Weighted score determines graduation velocity.
Three-Tier Storage Graduation
Tier 1: Friction Log (ephemeral, per-session)
Location: ~/.claude/friction/sessions/{date}-{id}.json
Retention: 30 days, then pruned
Threshold: 1 occurrence, logged, no action
Tier 2: Pattern Candidate (persistent, LEARNINGS.md)
Location: ~/.claude/skills/LEARNINGS.md (friction section)
Threshold: 3+ occurrences across 2+ sessions
Action: flagged for review in next friction report
Tier 3: Graduated Rule (CLAUDE.md or skill update)
Threshold: reviewed + user-approved
Action: permanent guidance added to project/user config
Constraint: NEVER auto-modify CLAUDE.mdGraduation Formula
graduation_score = (weighted_count * recency_factor) / sessions_seen
recency_factor:
last 7 days = 1.0
8-14 days = 0.7
15-30 days = 0.4
31+ days = 0.1
Tier 2 threshold: graduation_score >= 6.0
Tier 3 proposal: graduation_score >= 12.0Detection Workflow
Run at session end, at 80% context usage (via
conserve:clear-context), or after failed improvement
cycles (when abstract:metacognitive-self-mod detects
regression).
Step 1: Scan Session for Signals
For each friction indicator found, wrap it in the shared session-capture envelope (ADR-0011) so downstream readers can ingest friction signals and trace-capture entries through one parser:
{
"schema_version": "session-capture/1",
"session_id": "2026-04-14-abc12345",
"timestamp": "2026-04-14T10:23:00Z",
"source": "friction-detector",
"payload": {
"signal_type": "retry_loop",
"description": "rg command failed 3x, fell back to grep",
"context": "searching for pattern in node_modules",
"weight": "medium"
}
}Legacy files written before envelope adoption are read
as session-capture/0 (entire file treated as the
payload). See docs/adr/0011-session-capture-envelope.md
for the contract and migration path.
Step 2: Compare Against Existing Log
FRICTION_DIR=~/.claude/friction/sessions
mkdir -p "$FRICTION_DIR"
# Count prior occurrences of similar signals
if command -v rg &>/dev/null; then
rg -c "$SIGNAL_TYPE" "$FRICTION_DIR"/*.json 2>/dev/null || echo "0"
else
grep -rc "$SIGNAL_TYPE" "$FRICTION_DIR"/*.json 2>/dev/null || echo "0"
fiStep 3: Calculate Graduation Score
Aggregate across session logs: sum weighted occurrences, apply recency decay, divide by session count, compare against tier thresholds.
Step 4: Propose Graduations
Tier 2 crossing: append to LEARNINGS.md friction section. Tier 3 crossing: present proposal with evidence to user, wait for explicit approval before any modification.
Show full SKILL.md (216 more words)Show less
Step 5: Store Results
Write session log to
~/.claude/friction/sessions/{date}-{session_id}.json
and update ~/.claude/friction/index.json.
Anti-Noise Rules
Ignore these signals:
- One-off failures: transient network/CI errors (unless they recur 3+ times)
- User-initiated exploration: deliberate experimentation is not agent error
- Already-graduated patterns: covered by existing CLAUDE.md rules or skill instructions
- External tool failures: MCP server crashes and similar tool bugs unrelated to agent behavior
Decay factor: signals older than 30 days contribute only 10% of their original weight (see graduation formula recency_factor).
Friction Report Format
## Friction Report: Session {date}
### New Signals (Tier 1)
- [RETRY] `rg` command failed 3x, fell back to `grep`
- [RE-READ] Read SKILL.md 4 times (lost file structure context)
### Recurring Patterns (Tier 2 candidates)
- [CORRECTION] User corrected file path format 4x across 3 sessions
Score: 8.4 (threshold: 6.0)
Candidate: Add path format guidance to CLAUDE.md
### Graduation Proposals (Tier 3)
- [RULE] "Always use absolute paths in Read tool"
Evidence: 7 corrections across 5 sessions
Score: 14.2 (threshold: 12.0)
Action: Approve / Reject / Defer
### Noise Filtered
- 2 transient network timeouts (ignored)
- 1 user-initiated deep exploration (ignored)Integration
Feeds into: LEARNINGS.md (Tier 2 patterns, same
format as /abstract:aggregate-logs),
abstract:skill-improver (priority scoring), and
abstract:metacognitive-self-mod (pipeline
effectiveness).
Consumes from: session transcripts,
aggregate_learnings_daily hook data, and the
performance tracker for trend correlation.
When NOT to Use
- Single isolated failures (wait for recurrence)
- Skill authoring (use
abstract:skill-authoring) - Routine log aggregation (use
/abstract:aggregate-logs)
Related
abstract:metacognitive-self-mod: improvement analysisabstract:skills-eval: evaluation criteria/abstract:aggregate-logs: manual LEARNINGS.md generationconserve:clear-context: triggers friction scan at 80%
Exit Criteria
- Session friction report produced in "Friction Report Format" with at least one section (New Signals, Recurring Patterns, or Graduation Proposals) populated
- Each signal written as JSON to
~/.claude/friction/sessions/{date}-{session_id}.jsonvia thesession-capture/1schema - Patterns with
graduation_score>= 12.0 generate a Tier 3 proposal; skill does not auto-modify CLAUDE.md - Noise signals (network failures, user exploration) appear in "Noise Filtered" and are excluded from graduation scoring
© athola, 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 plugins/abstract/skills/friction-detector of athola/claude-night-market.
Open the folder on GitHubat commit 9f3eb00
Compare with similar skills
Friction Detector 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 |
|---|---|---|---|---|---|---|
| Friction Detector this skillathola/claude-night-market | 341 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Weekly Engineering Retrogarrytan/gstack | 136k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Dough Execute Planterryyin/lizard | 2.6k | — | ~4.3k | Automated safety check: Pass | Custom licence | |
| Oral Paper SkillAdkid-Zephyr/oral-paper-skill | 350 | — | ~1.9k | Automated safety check: Pass | None | |
| Deck Retroasheshgoplani/agent-deck | 1k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Dough Execution Retrospectiveterryyin/lizard | 2.6k | — | ~4k | Automated safety check: Pass | Custom licence |
Similar skills
Dough Execute Plan
terryyin/lizard
Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…
Oral Paper Skill
Adkid-Zephyr/oral-paper-skill
Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.
Deck Retro
asheshgoplani/agent-deck
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.
Dough Execution Retrospective
terryyin/lizard
Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup.
Criticism Self Criticism
HughYau/qiushi-skill
批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。
More from athola/claude-night-market
All 154 skills in this repoNight Market Diagnostics Toolkit
athola/claude-night-market
Run and interpret repo diagnostic scripts (ratchets, validators, token stats).
Skills Eval
athola/claude-night-market
Evaluate Claude skill quality through auditing. An agent skill from athola/claude-night-market.
Agent Teams
athola/claude-night-market
Coordinates Claude agent teams via filesystem protocol. An agent skill from athola/claude-night-market.
Delegation Core
athola/claude-night-market
Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer).
Elegant Code
athola/claude-night-market
Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage.
Skill Library Mission
athola/claude-night-market
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review.
Related
Categories
Questions about Friction Detector
What does Friction Detector do?
Detect friction signals; graduate patterns into rules. An agent skill from athola/claude-night-market. Friction Detector is an agent skill from athola/claude-night-market. Detect friction signals; graduate patterns into rules.
When should I use Friction Detector?
Friction Detector fits situations like: session retrospectives; tasks that involve Retrospectives.
How do I install Friction Detector in Claude Code?
Run `npx skills add athola/claude-night-market --skill friction-detector -a claude-code`. Or copy the skill folder (plugins/abstract/skills/friction-detector in athola/claude-night-market) into .claude/skills/friction-detector in your project. Claude Code loads it when a task matches its description.
How do I install Friction Detector in Codex?
Run `npx skills add athola/claude-night-market --skill friction-detector -a codex`. Or copy the skill folder (plugins/abstract/skills/friction-detector in athola/claude-night-market) into .agents/skills/friction-detector in your project. Codex loads it when a task matches its description.
Can I use Friction Detector 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 athola/claude-night-market --skill friction-detector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/friction-detector, .gemini/skills/friction-detector, .github/skills/friction-detector and .opencode/skills/friction-detector in your project.
What does Friction Detector need to run?
Going by SKILL.md and its folder, Friction Detector needs the command-line tools its instructions call (rg).
Does Friction Detector 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 Friction Detector 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 Friction Detector use?
Friction Detector 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 Friction Detector use?
About 1.8k tokens (SKILL.md is roughly 7.2k 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 Friction Detector?
Skills that share tags, products or a category with Friction Detector: Weekly Engineering Retro (garrytan/gstack, 136k stars), Dough Execute Plan (terryyin/lizard, 2.6k stars), Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 350 stars) and Deck Retro (asheshgoplani/agent-deck, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Friction Detector?
athola (a GitHub user) maintains it in athola/claude-night-market, which has 341 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 6, 2026.
Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.