Pixel-CLI/pixel / .agents/skills/pixel-retro
pixel-retro
VerifiedMine the last 24 h (or a given window) of pixel usage — every repo's `.pixel/actions.jsonl` plus the agent transcripts indexed by `pixel recall` (claude, codex, pi…) — for frictions pixel actually caused, verify each one against the current binary and code, and propose ranked, evidence-backed improvements (bug fix, error message, flag, agent prompt, rule, doc); for the pixel repo itself, also measure each pull request from first edit to validated CI and where agents sat idle (`lead_time.py`). Suggests only; implements nothing without the user's pick. Use when the user says "/pixel-retro", "retro pixel", "qu'est-ce qui a coincé avec pixel", "améliorations pixel depuis les transcripts", "pixel friction", "où l'agent attend", "bottleneck", "lead time", or asks what to improve in pixel or its development workflow from recent sessions.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 21.9 KB |
| adherence.py | script | 18.3 KB |
| lead_time.py | script | 22.7 KB |
| ledger.py | script | 1.5 KB |
| roots.py | script | 3.2 KB |
| slow.py | script | 5.6 KB |
| test_adherence.py | script | 9.6 KB |
| test_lead_time.py | script | 17.4 KB |
| test_slow.py | script | 2.4 KB |
test_slow.py
View on GitHub#!/usr/bin/env python3
# SPDX-FileCopyrightText: The Pixel contributors
# SPDX-License-Identifier: MIT
"""Contract of slow.py: each slow invocation counted once, in the repository it ran in.
The 2026-10-16 retro read one 7.3 s `find-symbol` as four, in four
repositories: a worktree bootstrap had copied the main checkout's
`actions.jsonl` into three Codex worktrees. A slow op that looks four
times as frequent and widespread outranks every real finding.
"""
import json
import pathlib
import sys
import tempfile
import unittest
sys.path.insert(0, str(pathlib.Path(__file__).parent))
import slow # noqa: E402
TS = 1_792_000_000_000
def line(invocation, cwd, ms=7349, command="find-symbol", **extra):
return json.dumps({"invocation_id": invocation, "ts_ms": TS, "pid": 1, "command": command,
"args": f"{command} x", "cwd": cwd, "duration_ms": ms,
"serve": [{"route": "daemon_started", "start_ms": ms}], **extra})
class Copies(unittest.TestCase):
def setUp(self):
self.dir = tempfile.TemporaryDirectory()
self.addCleanup(self.dir.cleanup)
def logs(self, *contents):
paths = []
for i, lines in enumerate(contents):
path = pathlib.Path(self.dir.name) / f"{i}.jsonl"
path.write_text("\n".join(lines) + "\n")
paths.append(str(path))
return paths
def test_a_line_copied_into_other_logs_is_one_invocation_in_its_own_repository(self):
main = line("32553-a-0", "/repo")
paths = self.logs([main], [main, line("2-b-0", "/wt/1")], [main])
groups, skipped, copies = slow.collect(paths, 0, 5000)
rows = groups[("find-symbol", "daemon_started", "-", "start_ms")]
self.assertEqual(sorted(r[1] for r in rows), ["2-b-0", "32553-a-0"])
# Repositories are where the calls ran, not the files holding them.
self.assertEqual({r[2] for r in rows}, {"/repo", "/wt/1"})
self.assertEqual((skipped, copies), (0, 2))
def test_lines_without_an_id_are_told_apart_by_pid_time_and_args(self):
bare = json.loads(line(None, "/repo"))
other = dict(bare, args="find-symbol y")
paths = self.logs([json.dumps(bare), json.dumps(other)], [json.dumps(bare)])
groups, _, copies = slow.collect(paths, 0, 5000)
self.assertEqual(sum(map(len, groups.values())), 2)
self.assertEqual(copies, 1)
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |