AI Daily Digest
vigorX777/ai-daily-digest
Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses AI to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category…
A skill your agent uses when making ANY code change to pytrendy, creating issues, or opening PRs.
$ npx skills add RussellSB/pytrendy --skill maintenance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RussellSB/pytrendy maintenance --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/RussellSB/pytrendy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/maintenance .claude/skills/maintenance && 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 "maintenance" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/maintenance into .claude/skills/maintenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maintenance", 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/RussellSB/pytrendy/tree/main/.opencode/skills/maintenanceType 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 RussellSB/pytrendy --skill maintenance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RussellSB/pytrendy maintenance --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/maintenance .agents/skills/maintenance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "maintenance" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/maintenance into .agents/skills/maintenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maintenance", 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 RussellSB/pytrendy --skill maintenance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RussellSB/pytrendy maintenance --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/maintenance .cursor/skills/maintenance && 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 "maintenance" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/maintenance into .cursor/skills/maintenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maintenance", 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/RussellSB/pytrendy.git --path .opencode/skills/maintenance--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 RussellSB/pytrendy --skill maintenance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RussellSB/pytrendy maintenance --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/maintenance .gemini/skills/maintenance && 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 "maintenance" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/maintenance into .gemini/skills/maintenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maintenance", 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 RussellSB/pytrendy maintenanceInstalls 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 RussellSB/pytrendy --skill maintenance -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/maintenance .github/skills/maintenance && 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 "maintenance" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/maintenance into .github/skills/maintenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maintenance", 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 RussellSB/pytrendy --skill maintenance -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RussellSB/pytrendy maintenance --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/maintenance .opencode/skills/maintenance && 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 "maintenance" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/maintenance into .opencode/skills/maintenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maintenance", 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.
maintenanceA skill your agent uses when making ANY code change to pytrendy, creating issues, or opening PRs.
Maintenance is an agent skill from RussellSB/pytrendy. Use when making ANY code change to pytrendy, creating issues, or opening PRs. Covers commit format, PR title conventions, branch model, deprecation policy, API surface, diff conventions, remote session behaviour, and things you must not touch. Load this FIRST before any code work.
Its SKILL.md is about 2.1k 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 Data & Analytics. The repository describes itself as: Trend Detection in Python. Applicable for real-world industry use cases in time series. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 0d6d5bb. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
gitpoetryFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Maintenance loads about 2.1k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 919 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.
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.
The full file from RussellSB/pytrendy at commit 0d6d5bb, republished under its MIT licence (© RussellSB). 919 words, ~2,118 tokens.
.claude/skills/maintenance/SKILL.md (or your agent's skills folder).CRITICAL: Before EVERY
git commit, verify the message matches^(feat|fix|docs|style|refactor|perf|test|build|ci|chore|revert)(\(.+\))?!?: .+. If not, rewrite it. No exceptions.CRITICAL: Before EVERY PR title creation, verify the title matches the same pattern.
lint-pr-title.ymlenforces this in CI — PRs with non-conforming titles are blocked.
The public API is what pytrendy/__init__.py exports plus the detect_trends() signature:
from pytrendy import detect_trends, load_data, plot_pytrendy, dtwdetect_trends(df, date_col, value_col, plot=True, method_params=None, debug=False) → PyTrendyResultsload_data(name) — name ∈ {'series_synthetic', 'classes_signals'} (CSVs in pytrendy/io/data/)plot_pytrendy(...) — annotated visualizationdtw — re-exported from pytrendy.simpledtwPyTrendyResults (from pytrendy.io.results_pytrendy) is the return type: .print_summary(), filtering by direction/rank, tabular segment access.
Changing any of these is user-observable. Internal helpers in post_processing/, process_signals.py, simpledtw.py are not public API — restructure freely with refactor:.
| Situation | Commit type | Version bump | Mechanism |
|---|---|---|---|
| Parameter still works but deprecated (soft) | feat: | minor | warnings.warn(..., DeprecationWarning) + keep accepting the old name |
| Parameter/behavior removed entirely (hard) | feat!: or BREAKING CHANGE: | major | Remove the old code path |
| Internal restructure, zero public API impact | refactor: | none | No warning needed |
Deprecating a public param is feat:, NOT refactor: — even if the code change is a rename. Deprecation is a user-facing signal that triggers a minor bump and documents intent to remove in a future major. See docs/contributing.md "Deprecations" and .github/copilot-instructions.md (now migrated here).
detect_trends(..., method_params=...): is_abrupt_padded is deprecated (raises DeprecationWarning, see pytrendy/detect_trends.py:63). Use abrupt_padding instead.
method_params keys (the only ones honored)method_params = {
'abrupt_padding': 0, # int: days to pad around abrupt transitions
'avoid_noise': True, # bool: skip noisy segments
}Any other keys passed are silently dropped — detect_trends reconstructs the dict from these two defaults (pytrendy/detect_trends.py:72). Don't add a third key without also updating this allowlist and the docstring.
mkdocs.yml). Required on public functions.debug=True in detect_trends for dev plots/prints — that's what it's for.refactor: PR.detect_trends() runs five stages in pytrendy/detect_trends.py:77:
process_signals(df, value_col, method_params, debug) — Savitzky-Golay smoothing, flat/noise flags.get_segments(df) — contiguous segment extraction with min-length: Up/Down ≥3d, Flat/Noise ≥1d.refine_segments(df, value_col, segments, method_params) — boundary adjust, DTW gradual/abrupt classification, abrupt shaving, grouping, artifact cleanup.analyse_segments(df, value_col, segments) — metrics: total/percent change, duration, SNR, change rank.plot_pytrendy(df, value_col, segments) — only if plot=True.Each stage's output is the next stage's input. See the pytrendy skill for the module map.
Segment dicts have at minimum: direction ('Up'/'Down'/'Flat'/'Noise'), start, end. After analyse_segments, also: days, total_change, change_rank, trend_class ('gradual'/'abrupt'/NaN). Tests in tests/conftest.py assert on direction/start/end — changing the keys or values breaks the whole suite.
develop, not main. check-base-branch.yml hard-fails otherwise. Only develop→main release PRs and automated docs/whats-new-* PRs bypass.main = stable release branch. develop = prerelease (dev channel).git checkout -b my-feature origin/develop.lint-pr-title.yml rejects titles not matching ^(feat|fix|docs|style|refactor|perf|test|build|ci|chore|revert)(\(.+\))?!?: .+.feat→minor, fix→patch, !/BREAKING CHANGE:→major, others→no bump.feat: (minor), not refactor: — see "Deprecation policy" section above.chore vs fix: fix: triggers a patch release via semantic-release. Use chore: or ci: for maintenance-only changes that have zero user-facing code impact. Using fix: on non-bugfix work causes accidental auto-releases.pyproject.toml version — bumped by semantic-release via poetry version. Editing it by hand breaks releases.CHANGELOG.md — generated by semantic-release on main.docs/whats-new.md — generated by the agentic whats-new.yaml workflow (OpenCode CLI writes between <!-- WHATS_NEW_CONTENT_START/END --> sentinels). Don't edit by hand unless explicitly directed to fix/regenerate an entry — the workflow overwrites content between the sentinels on the next release.When creating issues or PRs, follow the conventions in docs/contributing.md:
[Tag] Short description format: [Bug], [Docs], [Enhancement], [Feature], [CI], [Maintenance]feat: ..., fix: ..., etc. (same as commit messages)Closes #<number>bug, documentation, enhancement, feature, test, maintenance, good first issue, priorityDetecting CI environment: When PYTRENDY_CI=true is set, you are running in a GitHub Actions environment, not a local interactive session.
main or develop© RussellSB, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .opencode/skills/maintenance of RussellSB/pytrendy.
Open the folder on GitHubat commit 0d6d5bb
Maintenance 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 |
|---|---|---|---|---|---|---|
| Maintenance this skillRussellSB/pytrendy | 106 | — | ~2.1k | Automated safety check: Pass | MIT | |
| AI Daily DigestvigorX777/ai-daily-digest | 1.6k | — | ~1.3k | Automated safety check: Pass | None | |
| Documd Visualsmarkdown-viewer/skills | 3.4k | — | ~3.3k | Automated safety check: Pass | CC-BY-4.0 | |
| Retentioneering Contributingretentioneering/retentioneering-tools | 925 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Agentic Kaggle WorkflowFrankS-IntelLab/agentic-kaggle-skill | 188 | — | ~4k | Automated safety check: Pass | MIT | |
| Billing Reviewpolarsource/polar | 10k | — | ~2.3k | Automated safety check: Pass | MIT |
vigorX777/ai-daily-digest
Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses AI to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category…
markdown-viewer/skills
Create text-driven visuals in Markdown: charts, diagrams, cards, architecture and page layouts.
retentioneering/retentioneering-tools
Help the user turn their Retentioneering ideas, friction reports, bug findings, or feature needs into high-quality upstream contributions: from capturing and validating the idea, through minimal…
FrankS-IntelLab/agentic-kaggle-skill
Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.
polarsource/polar
Review a diff that touches Polar's billing domain — subscriptions, cycles and crons, orders, billing entries, meters and usage, discounts, checkout, payments and dunning, refunds, disputes, payouts…
dkedar7/fast_dash
Build a Fast Dash web app from a Python function. An agent skill from dkedar7/fast_dash.
RussellSB/pytrendy
A skill your agent uses when debugging a pytrendy bug, reproducing a regression, or inspecting intermediate pipeline stage output.
RussellSB/pytrendy
A skill your agent uses when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body.
RussellSB/pytrendy
A skill your agent uses when working on pytrendy code, tests, or data.
RussellSB/pytrendy
A skill your agent uses when touching .github/workflows/, release config (.releaserc), mkdocs.yml, docs deploy, or the whats-new generator.
Categories
A skill your agent uses when making ANY code change to pytrendy, creating issues, or opening PRs. Maintenance is an agent skill from RussellSB/pytrendy. Use when making ANY code change to pytrendy, creating issues, or opening PRs.
Maintenance fits situations like: making ANY code change to pytrendy; creating issues.
Run `npx skills add RussellSB/pytrendy --skill maintenance -a claude-code`. Or copy the skill folder (.opencode/skills/maintenance in RussellSB/pytrendy) into .claude/skills/maintenance in your project. Claude Code loads it when a task matches its description.
Run `npx skills add RussellSB/pytrendy --skill maintenance -a codex`. Or copy the skill folder (.opencode/skills/maintenance in RussellSB/pytrendy) into .agents/skills/maintenance in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RussellSB/pytrendy --skill maintenance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maintenance, .gemini/skills/maintenance, .github/skills/maintenance and .opencode/skills/maintenance in your project.
Going by SKILL.md and its folder, Maintenance needs the command-line tools its instructions call (git and poetry). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Maintenance is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Maintenance: AI Daily Digest (vigorX777/ai-daily-digest, 1.6k stars), Documd Visuals (markdown-viewer/skills, 3.4k stars), Retentioneering Contributing (retentioneering/retentioneering-tools, 925 stars) and Agentic Kaggle Workflow (FrankS-IntelLab/agentic-kaggle-skill, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
RussellSB (a GitHub user) maintains it in RussellSB/pytrendy, which has 106 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: RussellSB/pytrendy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.