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

Tiger Correctness Remediation

by safreita1 in safreita1/TIGER

Repair and verify TIGER algorithms, simulations, measures, graph utilities, packaging, examples, and tests against their documented and literature-defined behavior while preserving the repository's…

MITAuto-check passedDevelopment

Install Tiger Correctness Remediation

skills CLI
$ npx skills add safreita1/TIGER --skill tiger-correctness-remediation -a claude-code

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

GitHub CLI
$ gh skill install safreita1/TIGER tiger-correctness-remediation --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/safreita1/TIGER.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tiger-correctness-remediation .claude/skills/tiger-correctness-remediation && 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
tiger-correctness-remediation
GitHub stars
165
Token cost
~1.4k tokens
SKILL.md length
689 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Repair and verify TIGER algorithms, simulations, measures, graph utilities, packaging, examples, and tests against their documented and literature-defined behavior while preserving the repository's…

  • Works in 9 steps: Confirm the active branch is… → Inspect the target function, its… → Identify the exact contract: inputs,… → …
  • Work on the correctness-remediation branch
  • SKILL.md covers Source of truth, Required workflow, Style preservation and Scientific verification, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tiger Correctness Remediation is an agent skill from safreita1/TIGER. Repair and verify TIGER algorithms, simulations, measures, graph utilities, packaging, examples, and tests against their documented and literature-defined behavior while preserving the repository's existing style. Use for work on the correctness-remediation branch or any TIGER correctness review.

Its SKILL.md is about 1.4k 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. The repository describes itself as: Python toolbox to evaluate graph vulnerability and robustness (CIKM 2021). The licence is MIT.

When your agent uses it

  • Work on the correctness-remediation branch
  • Any TIGER correctness review

Example prompts

  • “/tiger-correctness-remediation”

Requirements

  • Python 3

Workflow steps

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

  1. Confirm the active branch is codex/correctness-remediation or a child branch created for one issue cluster.
  2. Inspect the target function, its docstring, neighboring functions, existing tests, examples, and cited source before editing.
  3. Identify the exact contract: inputs, outputs, state transition, mutation policy, randomness, numerical precision, and failure behavior.
  4. Add or enable the smallest deterministic regression that fails for the audited reason.
  5. Make the smallest production change that satisfies the contract.
  6. Run the focused test file, the relevant neighboring test files, and then the full suite.
  7. Inspect the diff for unrelated formatting, import churn, or behavior changes.
  8. Update documentation and citations in the same change whenever a mathematical contract changes.
  9. Record the addressed issue IDs in the commit message or pull-request description.

What it can do on your machine

Read from SKILL.md and the folder at commit 60ebc3f. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Tiger Correctness Remediation loads about 1.4k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 689 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 safreita1/TIGER at commit 60ebc3f, republished under its MIT licence (© safreita1). 689 words, ~1,378 tokens.

Download SKILL.mdSave it as .claude/skills/tiger-correctness-remediation/SKILL.md (or your agent's skills folder).
name
tiger-correctness-remediation
description
Repair and verify TIGER algorithms, simulations, measures, graph utilities, packaging, examples, and tests against their documented and literature-defined behavior while preserving the repository's existing style. Use for work on the correctness-remediation branch or any TIGER correctness review.

TIGER Correctness Remediation

Use this skill when reviewing or fixing correctness in the TIGER repository.

Source of truth

Read ../../../CORRECTNESS_REMEDIATION_PLAN.md before making changes. Treat its scientific contracts, issue IDs, delivery phases, and acceptance criteria as the working specification.

Required workflow

  1. Confirm the active branch is codex/correctness-remediation or a child branch created for one issue cluster.
  2. Inspect the target function, its docstring, neighboring functions, existing tests, examples, and cited source before editing.
  3. Identify the exact contract: inputs, outputs, state transition, mutation policy, randomness, numerical precision, and failure behavior.
  4. Add or enable the smallest deterministic regression that fails for the audited reason.
  5. Make the smallest production change that satisfies the contract.
  6. Run the focused test file, the relevant neighboring test files, and then the full suite.
  7. Inspect the diff for unrelated formatting, import churn, or behavior changes.
  8. Update documentation and citations in the same change whenever a mathematical contract changes.
  9. Record the addressed issue IDs in the commit message or pull-request description.

Style preservation

  • Match nearby imports, blank lines, naming, dictionaries, loops, comments, and docstrings.
  • Keep tests as top-level test_* functions with direct assert statements and the existing main() runner.
  • Do not introduce pytest fixtures, decorators, parametrization, Hypothesis, formatters, or broad mechanical rewrites unless the owner explicitly requests them.
  • Do not reorder or reformat unaffected code.
  • Prefer a short local helper only when it removes repetition in the same style already used by the repository.

Scientific verification

Diffusion
  • Preserve synchronous discrete-time SIS/SIR semantics.
  • Transmission is independent per infected-susceptible edge with probability b.
  • Recovery applies to nodes infected at the start of the step with probability d.
  • SIS recovery returns to susceptible; SIR recovery is permanent.
  • Newly infected nodes act starting in the next step.
  • Validate model names, probabilities, initial fraction, runs, and steps.
Cascading failure
  • Do not call a model Crucitti or Motter-Lai unless its load, capacity, failure, recomputation/redistribution, and robustness equations match the cited source.
  • Keep node failures and edge failures in distinct state.
  • Use synchronous failure updates.
  • Prove load conservation where a redistribution model is used.
  • Never process the same failed load twice.
  • Never mutate the caller's graph.
Crucitti cascading failures
  • Keep overloaded nodes in the functioning graph; only the initial trigger is removed.
  • Set fixed capacity to (1 + r) L_i(0), with positive r.
  • Update incident edge efficiencies synchronously from the capacity-to-load ratio.
  • Route over paths minimizing the sum of reciprocal edge efficiencies.
  • Report average weighted network efficiency, not largest-component size.
  • Verify degradation, recovery, weighted route selection, and caller-graph preservation.
Show full SKILL.md (270 more words)Show less
Python compatibility
  • Exercise core behavior on Python 3.8 through 3.14.
  • Exercise the complete optional visualization stack on the latest stable Python.
  • Do not retain dependency pins that make a declared Python version unsatisfiable.
Measures
  • Verify formulas on analytically solvable toy graphs.
  • Check algorithm branches on both sides of size thresholds.
  • Preserve graph order in standard normalizations.
  • Distinguish an explicit approximation from an exact default.
  • Avoid global numerical-state changes and premature rounding.
Attacks and defenses
  • Preserve arbitrary node labels.
  • Validate k against the feasible node, edge, or nonedge set.
  • Every added edge must be a feasible nonedge and not a self-loop.
  • Every removed edge must exist in the working graph.
  • Rewiring must apply removal and addition to the same simulation copy.
  • Node protection removes attacked - protected.

Test design

  • Use paths, cycles, stars, complete graphs, empty graphs, disconnected graphs, and small labeled graphs.
  • Prefer exact closed forms and state sets to approximate aggregate inequalities.
  • For random behavior, assert same-seed reproducibility and different-seed divergence on fixtures where the result is deterministic for those seeds.
  • Add boundary cases for zero, one, maximum feasible, impossible, negative, and unknown inputs.
  • Test caller-state preservation and repeated runs.
  • Do not resolve a failing regression by weakening its assertion unless the scientific contract was explicitly revised.

Completion checklist

  • The focused regression fails before the fix and passes after it.
  • Existing tests are updated only when they encoded the audited wrong behavior.
  • Relevant examples and documentation agree with the corrected behavior.
  • Optional visualization dependencies do not block core imports.
  • The full suite passes.
  • The diff contains no unrelated style changes.
  • The issue ledger and release notes reflect the final decision.

© safreita1, 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 .agents/skills/tiger-correctness-remediation of safreita1/TIGER.

Open the folder on GitHubat commit 60ebc3f

Compare with similar skills

Tiger Correctness Remediation 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.

Tiger Correctness Remediation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tiger Correctness Remediation this skillsafreita1/TIGER165—~1.4kAutomated safety check: PassMIT
Diagram Designcathrynlavery/diagram-design49k1 repos~7.6kAutomated safety check: PassMIT
R Function Input Validationtidyverse/dplyr5.1k1 repos~2.3kAutomated safety check: PassCustom licence
Archifymolvqingtai/WebChat2.6k—~5.6kAutomated safety check: PassMIT
JSON Processing with jqcharmbracelet/crush29k—~746Automated safety check: PassCustom licence
Kimi WebbridgeMoonshotAI/kimi-code7.8k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    49k GitHub starsUsed in 1 repo~7.6k tokens
    DevelopmentAuto-check passed

  • R Function Input Validation

    tidyverse/dplyr

    Validates arguments of exported R functions with the standalone check_* type checkers from rlang, in tidyverse style with clear error messages.

    5.1k GitHub starsUsed in 1 repo~2.3k tokens
    DevelopmentAuto-check passed

  • Archify

    molvqingtai/WebChat

    Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone HTML files with SVG graphics, a built-in dark/light theme toggle, and one-click export to…

    2.6k GitHub stars~5.6k tokensUpdated 28 days ago
    DevelopmentAuto-check passed

  • JSON Processing with jq

    charmbracelet/crush

    Explains the jq command built into Crush for querying, filtering and reshaping JSON, including its supported flags and where it differs from standard jq.

    29k GitHub stars~746 tokensUpdated today
    DevelopmentAuto-check passed

  • Kimi Webbridge

    MoonshotAI/kimi-code

    Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login…

    7.8k GitHub stars~3.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Scientific Schematics

    spacering-net/codeg

    Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement.

    3.9k GitHub starsUsed in 11 repos~5.9k tokens
    DevelopmentAuto-check: notes

More from safreita1/TIGER

  • Tiger Release

    safreita1/TIGER

    Prepare and publish a TIGER release by keeping implementation, tests, source and hosted documentation, citations, version metadata, GitHub, and PyPI artifacts synchronized.

    165 GitHub stars~1.8k tokensUpdated 27 days ago
    Auto-check passed

Categories

Questions about Tiger Correctness Remediation

What does Tiger Correctness Remediation do?

Repair and verify TIGER algorithms, simulations, measures, graph utilities, packaging, examples, and tests against their documented and literature-defined behavior while preserving the repository's…. Tiger Correctness Remediation is an agent skill from safreita1/TIGER. Repair and verify TIGER algorithms, simulations, measures, graph utilities, packaging, examples, and tests against their documented and literature-defined behavior while preserving the repository's existing style.

When should I use Tiger Correctness Remediation?

Tiger Correctness Remediation fits situations like: work on the correctness-remediation branch; any TIGER correctness review.

How do I install Tiger Correctness Remediation in Claude Code?

Run `npx skills add safreita1/TIGER --skill tiger-correctness-remediation -a claude-code`. Or copy the skill folder (.agents/skills/tiger-correctness-remediation in safreita1/TIGER) into .claude/skills/tiger-correctness-remediation in your project. Claude Code loads it when a task matches its description.

How do I install Tiger Correctness Remediation in Codex?

Run `npx skills add safreita1/TIGER --skill tiger-correctness-remediation -a codex`. Or copy the skill folder (.agents/skills/tiger-correctness-remediation in safreita1/TIGER) into .agents/skills/tiger-correctness-remediation in your project. Codex loads it when a task matches its description.

Can I use Tiger Correctness Remediation 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 safreita1/TIGER --skill tiger-correctness-remediation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tiger-correctness-remediation, .gemini/skills/tiger-correctness-remediation, .github/skills/tiger-correctness-remediation and .opencode/skills/tiger-correctness-remediation in your project.

What does Tiger Correctness Remediation need to run?

SKILL.md names no scripts, command-line tools or credentials: Tiger Correctness Remediation is instructions for the agent only. Our summary lists: Python 3.

Does Tiger Correctness Remediation 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 Tiger Correctness Remediation 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 Tiger Correctness Remediation use?

Tiger Correctness Remediation 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 Tiger Correctness Remediation use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Tiger Correctness Remediation?

Skills that share tags, products or a category with Tiger Correctness Remediation: Diagram Design (cathrynlavery/diagram-design, 49k stars), R Function Input Validation (tidyverse/dplyr, 5.1k stars), Archify (molvqingtai/WebChat, 2.6k stars) and JSON Processing with jq (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tiger Correctness Remediation?

safreita1 (a GitHub user) maintains it in safreita1/TIGER, which has 165 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 13, 2026.

Source: safreita1/TIGER on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.