New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Anchor Repro

by lynxlangya in lynxlangya/techne

Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.

MITAuto-check passedTesting & QA

Install Anchor Repro

skills CLI
$ npx skills add lynxlangya/techne --skill anchor-repro -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lynxlangya/techne anchor-repro --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lynxlangya/techne.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/anchor-repro .claude/skills/anchor-repro && rm -rf skills-src

Use ~/.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/

Facts

Skill name
anchor-repro
GitHub stars
105
Token cost
~1.2k tokens
SKILL.md length
536 words
Files
6 (incl. scripts)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.

  • Works in 8 steps: Capture the symptom and stable anchor.… → Locate, then probe. Read enough code to… → Demonstrate. Run the probe through → …
  • Observable behavior that should change
  • SKILL.md covers Trigger Check, Forced Procedure, Ledger Usage and Stop Conditions
  • Runs Python scripts from its folder; calls python3

What it does

Anchor Repro is an agent skill from lynxlangya/techne. Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe. Use for bug reports, failing tests, crashes, hangs, regressions, wrong output, and observable behavior that should change.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `README-CN.md`, `README.md` and `eval.md`).

It sits in Testing & QA, covering Failing and flaky tests and QA and bug reports. The repository describes itself as: Forcing-function skills for AI agents — validated to improve behavior, not just change it. The licence is MIT.

When your agent uses it

  • Observable behavior that should change
  • Tasks that involve Failing and flaky tests
  • Tasks that involve QA and bug reports

Example prompts

  • “/anchor-repro”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Capture the symptom and stable anchor. Choose the most stable literal
  2. Locate, then probe. Read enough code to place the behavior. Pick the
  3. Demonstrate. Run the probe through
  4. Diagnose against the probe. Test hypotheses with discriminating runs
  5. Fix.
  6. Verify with the identical probe identity. Re-run the same execution mode,
  7. Promote when possible. If the target repo has a test suite, promote the
  8. Report. Cite the close JSON, cite the first repro entry's git evidence,

What it can do on your machine

Read from SKILL.md and the folder at commit 56bbe71. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Anchor Repro loads about 1.2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 536 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from lynxlangya/techne at commit 56bbe71, republished under its MIT licence (© lynxlangya). 536 words, ~1,183 tokens.

Download SKILL.mdSave it as .claude/skills/anchor-repro/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
anchor-repro
description
Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe. Use for bug reports, failing tests, crashes, hangs, regressions, wrong output, and observable behavior that should change.

anchor-repro

Force the skipped move in debugging: observe the bug before editing, then prove the fix with the same observation.

Trigger Check

Use this skill when the task is to correct observable behavior that is currently wrong: a failing test, error message, stack trace, regression, crash, hang, wrong return value, wrong render, or "X does Y; it should do Z."

Do not use it for new features, refactors, renames, formatting, docs/copy changes, dependency bumps without a behavioral symptom, or performance work without a measurable probe.

Boundary test: can the wrongness be written as "running X currently produces Y; it should produce Z"? If yes, use this skill and make X the probe seed. If the statement cannot be formed from current information, ask for or find the missing observation before editing.

Forced Procedure

  1. Capture the symptom and stable anchor. Choose the most stable literal substring of the observable symptom for --expect. Omit heap addresses, PIDs, timestamps, temp paths, and wrapped fragments. Use --expect whenever the symptom has stable text. If no stable text exists, --no-stable-expect is the honest fallback, not an unanchored run; do not use it when stable textual output exists.
  2. Locate, then probe. Read enough code to place the behavior. Pick the smallest CLI probe that exercises the reported symptom. In workspaces or monorepos, run from the package with --cwd <package-dir>, not with a cd ... && convention. If required environment changes matter, encode them inside --shell as one quoted command string such as 'VAR=... command'; inherited environment changes are not part of probe identity in v1.
  3. Demonstrate. Run the probe through scripts/repro_ledger.py run --project <root> --bug <slug> ... -- <command>. Read the failing output and confirm it fails for the reported reason: mechanically, expectMatched should be true when --expect was supplied; procedurally, inspect the tail/context instead of trusting an exit code.
  4. Diagnose against the probe. Test hypotheses with discriminating runs before stacking edits. If a better probe is needed, the new probe starts a new fail -> pass cycle and must be observed failing too.
  5. Fix.
  6. Verify with the identical probe identity. Re-run the same execution mode, argv vector or shell string, --cwd, and --timeout. Then run scripts/repro_ledger.py close --project <root> --bug <slug>.
  7. Promote when possible. If the target repo has a test suite, promote the probe into a committed regression test. This is encouraged, not a gate.
  8. Report. Cite the close JSON, cite the first repro entry's git evidence, name the strength rung from reference.md, and carry speculative when the ledger took an unreproduced path.
Show full SKILL.md (114 more words)Show less

Ledger Usage

Run and record a probe:

bash
python3 skills/anchor-repro/scripts/repro_ledger.py run \
  --project /path/to/project \
  --bug login-crash \
  --cwd packages/app \
  --expect "TypeError: cannot read" \
  --timeout 60 \
  -- npm test -- login.test.ts

Verify after the fix:

bash
python3 skills/anchor-repro/scripts/repro_ledger.py run \
  --project /path/to/project \
  --bug login-crash \
  --cwd packages/app \
  --expect "TypeError: cannot read" \
  --timeout 60 \
  -- npm test -- login.test.ts

python3 skills/anchor-repro/scripts/repro_ledger.py close \
  --project /path/to/project \
  --bug login-crash

Mark an honestly speculative fix only when reproduction is impossible:

bash
python3 skills/anchor-repro/scripts/repro_ledger.py mark-unreproduced \
  --project /path/to/project \
  --bug customer-only-crash \
  --no-probe-possible \
  --reason "Requires customer-only data and credentials unavailable in this environment"

The ledger writes target-project artifacts under .techne/repro/ and idempotently adds .techne/ to the target project's .gitignore. Do not commit .techne/ output.

Stop Conditions

  • Stop before editing if you have not run a failing probe or recorded an explicit mark-unreproduced path.
  • Stop if a failing run does not match the reported symptom; a hollow failure is not a reproduction.
  • Stop if a passing post-fix run uses a different identity; changed probes need their own fail -> pass cycle.
  • Stop before claiming a non-speculative fix if close does not exit 0 with a verified same-probe summary.

© lynxlangya, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts) in skills/anchor-repro of lynxlangya/techne.

  • SKILL.md
  • README-CN.md
  • README.md
  • eval.md
  • reference.md
  • scripts/repro_ledger.py

Open the folder on GitHubat commit 56bbe71

Compare with similar skills

Anchor Repro 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.

Anchor Repro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Anchor Repro this skilllynxlangya/techne105—~1.2kAutomated safety check: PassMIT
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Issue TracerZaxbyHub/opencode-swarm494—~383Automated safety check: PassMIT
Issue TracerZaxbyHub/opencode-swarm494—~397Automated safety check: PassMIT
Fixavibebuilder/claude-prime120—~1kAutomated safety check: PassMIT
Bug Reproduction Test GeneratorArabelaTso/Skills-4-SE253—~1.8kAutomated safety check: PassApache-2.0

Similar skills

  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Issue Tracer

    ZaxbyHub/opencode-swarm

    A skill your agent uses when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing…

    494 GitHub stars~383 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Issue Tracer

    ZaxbyHub/opencode-swarm

    A skill your agent uses when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing…

    494 GitHub stars~397 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Fix

    avibebuilder/claude-prime

    Fix bugs and broken behavior when there is enough evidence to act on a repair path.

    120 GitHub stars~1k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed

  • Bug Reproduction Test Generator

    ArabelaTso/Skills-4-SE

    Automatically generates executable tests that reproduce reported bugs from issue reports and code repositories.

    253 GitHub stars~1.8k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Diagnose Playwright Failure as Product Bug

    appsmithorg/appsmith

    Investigates a stubbornly failing Playwright test as a possible product bug, using error output, screenshots, traces and server code, and writes a structured bug report.

    41k GitHub stars~1.5k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from lynxlangya/techne

  • Anchor Intake

    lynxlangya/techne

    Interrogate a written engineering implementation brief before work starts.

    105 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Anchor Vet

    lynxlangya/techne

    Evidence-gated diff review for PRs, branches, commit ranges, staged code changes, and merge readiness checks.

    105 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Anchor Viz

    lynxlangya/techne

    Draw a faithful architecture or structure diagram of a real codebase or project by scanning the actual repo, never guessing.

    105 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Anchor Repro

What does Anchor Repro do?

Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe. Anchor Repro is an agent skill from lynxlangya/techne. Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.

When should I use Anchor Repro?

Anchor Repro fits situations like: observable behavior that should change; tasks that involve Failing and flaky tests; tasks that involve QA and bug reports.

How do I install Anchor Repro in Claude Code?

Run `npx skills add lynxlangya/techne --skill anchor-repro -a claude-code`. Or copy the skill folder (skills/anchor-repro in lynxlangya/techne) into .claude/skills/anchor-repro in your project. Claude Code loads it when a task matches its description.

How do I install Anchor Repro in Codex?

Run `npx skills add lynxlangya/techne --skill anchor-repro -a codex`. Or copy the skill folder (skills/anchor-repro in lynxlangya/techne) into .agents/skills/anchor-repro in your project. Codex loads it when a task matches its description.

Can I use Anchor Repro 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 lynxlangya/techne --skill anchor-repro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/anchor-repro, .gemini/skills/anchor-repro, .github/skills/anchor-repro and .opencode/skills/anchor-repro in your project.

What does Anchor Repro need to run?

Going by SKILL.md and its folder, Anchor Repro needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Anchor Repro 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 Anchor Repro 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Anchor Repro use?

Anchor Repro 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 Anchor Repro use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Anchor Repro?

Skills that share tags, products or a category with Anchor Repro: Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Issue Tracer (ZaxbyHub/opencode-swarm, 494 stars), Issue Tracer (ZaxbyHub/opencode-swarm, 494 stars) and Fix (avibebuilder/claude-prime, 120 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Anchor Repro?

lynxlangya (a GitHub user) maintains it in lynxlangya/techne, which has 105 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on July 2, 2026.

Source: lynxlangya/techne on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.