Suggestion Box
paperclipai/paperclip
Quietly suggest a concrete improvement after observing material, generalizable friction in agent work.
Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed.
Apache-2.0Auto-check passed
Install Suggesting Remedies
$ npx skills add Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Netflix-Skunkworks/oci-agent suggesting-remedies --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/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/suggesting-remedies .claude/skills/suggesting-remedies && 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 "suggesting-remedies" agent skill from https://github.com/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remedies into .claude/skills/suggesting-remedies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suggesting-remedies", 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/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remediesType 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 Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Netflix-Skunkworks/oci-agent suggesting-remedies --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/suggesting-remedies .agents/skills/suggesting-remedies && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "suggesting-remedies" agent skill from https://github.com/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remedies into .agents/skills/suggesting-remedies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suggesting-remedies", 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 Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Netflix-Skunkworks/oci-agent suggesting-remedies --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/suggesting-remedies .cursor/skills/suggesting-remedies && 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 "suggesting-remedies" agent skill from https://github.com/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remedies into .cursor/skills/suggesting-remedies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suggesting-remedies", 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/Netflix-Skunkworks/oci-agent.git --path skills/suggesting-remedies--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 Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Netflix-Skunkworks/oci-agent suggesting-remedies --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/suggesting-remedies .gemini/skills/suggesting-remedies && 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 "suggesting-remedies" agent skill from https://github.com/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remedies into .gemini/skills/suggesting-remedies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suggesting-remedies", 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 Netflix-Skunkworks/oci-agent suggesting-remediesInstalls 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 Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/suggesting-remedies .github/skills/suggesting-remedies && 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 "suggesting-remedies" agent skill from https://github.com/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remedies into .github/skills/suggesting-remedies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suggesting-remedies", 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 Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Netflix-Skunkworks/oci-agent suggesting-remedies --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/suggesting-remedies .opencode/skills/suggesting-remedies && 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 "suggesting-remedies" agent skill from https://github.com/Netflix-Skunkworks/oci-agent/tree/main/skills/suggesting-remedies into .opencode/skills/suggesting-remedies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suggesting-remedies", 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
suggesting-remedies- GitHub stars
- 144
- Token cost
- ~916 tokens
- SKILL.md length
- 472 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed.
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Suggesting Remedies is an agent skill from Netflix-Skunkworks/oci-agent. Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed. Keywords: - covariate balance failure, overlap warning, placebo warning - ATOTHRESHOLD, trimming extreme propensities - changing estimand: ATE → ATT, ATE → ATO - adding covariates, dataset insufficiency - actor-critic feedback loop, suggested spec changes
Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The licence is Apache-2.0.
Example prompts
- “/suggesting-remedies”
What it can do on your machine
Read from SKILL.md and the folder at commit a978030. 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
Suggesting Remedies loads about 916 tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 472 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 Netflix-Skunkworks/oci-agent at commit a978030, republished under its Apache-2.0 licence (© Netflix-Skunkworks). 472 words, ~916 tokens.
Download SKILL.mdSave it as
.claude/skills/suggesting-remedies/SKILL.md (or your agent's skills folder).- name
- suggesting-remedies
- description
- Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed. Keywords: - covariate balance failure, overlap warning, placebo warning - ATO_THRESHOLD, trimming extreme propensities - changing estimand: ATE → ATT, ATE → ATO - adding covariates, dataset insufficiency - actor-critic feedback loop, suggested spec changes
- Trimming, raising ATO_THRESHOLD, or any sample restriction by propensity changes the estimand from the ATE to the ATO (at the chosen threshold). Never suggest "trim the ATE" or an "ATE trimming threshold" — those are contradictions. Suggest switching the estimand to ATO instead, and call out the estimand change explicitly.
Covariate Balance
- A failure means treatment and control units differ systematically in at least one confounder.
- Most likely affects the ATE — not every population covariate profile is well-represented in all treatment levels.
- Remedies: switch the estimand to ATT or ATO; raise ATO_THRESHOLD above 0.1 to trim extreme propensities; manually trim units with extreme values of the problematic covariates.
- Note in the report that all three remedies change the estimand away from the ATE.
Overlap
- A warning means many units have propensity scores near 0 or 1 (near-deterministic assignment).
- Not a hard fail — the estimator stays consistent — but extreme inverse weights cause instability and make counterfactuals depend on a few observations.
- Remedies: switch the estimand to ATT or ATO; trim by raising ATO_THRESHOLD. Note that trimming changes the estimand to the ATO at the chosen threshold.
Placebo
- A warning means a placebo outcome — known to be unaffected by treatment — has a statistically significant effect after adjustment.
- Not disqualifying: the placebo outcome is already controlled for in the actual analysis.
- The report MUST state that a placebo failure signals (a) high sensitivity of the results to a single confounder, and (b) likely residual confounding from variables the model has not captured.
- Primary remedy (MUST appear in suggestions whenever placebo warns): find and add covariates that explain the placebo outcome. These are the variables most likely driving the residual confounding. Identify candidates by training a model with the placebo as the target and inspecting which existing covariates have the highest feature importance — then add covariates that capture the same signal as those drivers.
- If the spec's covariate set already exhausts what's available in the dataset (e.g., the eval uses every x_* column), the report MUST explicitly state that the dataset may be insufficient for a credible analysis. Do not silently fall through to model-flexibility remedies.
- Propensity / outcome model flexibility (see Propensity model below) is a secondary remedy for placebo failures — list it only after the covariate-set remedy or the dataset-insufficiency note, never as the headline placebo response.
Show full SKILL.md (89 more words)Show less
Propensity model
- Covariate balance failures and placebo warnings often indicate the propensity model is misspecified — it isn't capturing the true treatment-assignment process.
- Remedies: enable AUGMENT_CONTINUOUS_COVARIATES to add polynomial and bin-encoded versions of continuous features; switch to a more flexible propensity learner (e.g., gradient-boosted or deeper trees).
- These remedies do not change the estimand.
- If the propensity learner is already a flexible nonlinear model (e.g., XGBoost / LightGBM with sufficient depth and trees), augmentation is less likely to help — prefer adding more covariates, or accept that some confounding may be unobserved.
© Netflix-Skunkworks, Apache-2.0. 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 skills/suggesting-remedies of Netflix-Skunkworks/oci-agent.
Open the folder on GitHubat commit a978030
Compare with similar skills
Suggesting Remedies 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 |
|---|---|---|---|---|---|---|
| Suggesting Remedies this skillNetflix-Skunkworks/oci-agent | 144 | — | ~916 | Automated safety check: Pass | Apache-2.0 | |
| Suggestion Boxpaperclipai/paperclip | 100k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Network Bgp Diagnosticsaffaan-m/ECC | 277k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Triage Snmp Diagnosticsnetdata/netdata | 81k | — | ~3k | Automated safety check: Pass | GPL-3.0 | |
| Adding Ty Diagnosticsastral-sh/ruff | 50k | — | ~556 | Automated safety check: Pass | MIT | |
| Remediationdavepoon/buildwithclaude | 3.6k | — | ~3.8k | Automated safety check: Notes | MIT |
Similar skills
Network Bgp Diagnostics
affaan-m/ECC
Diagnostics-only BGP troubleshooting patterns for neighbor state, route exchange, prefix policy, AS path inspection, and safe evidence collection.
Triage Snmp Diagnostics
netdata/netdata
Investigate captured SNMP diagnostics and support bundles, or review diagnostics-tool and evidence-interpretation changes.
- Official
Adding Ty Diagnostics
astral-sh/ruff
A skill your agent uses when a user says "add a ty rule", "add a ty diagnostic", "write this new ty diagnostic", "change a ty error message", "review ty diagnostics", or asks to add, update, or…
Remediation
davepoon/buildwithclaude
Get a context-aware remediation plan for a vulnerability with fix verification steps
- Official
Suggest Automations
n8n-io/n8n
Offer the three most common automations for a user as a single-choice card, from your own knowledge of their team and their apps, then build the one they choose once they confirm, or offer more.
More from Netflix-Skunkworks/oci-agent
Changing Notebooks
Netflix-Skunkworks/oci-agent
Invoke this skill when making any modification to a notebook (.ipynb) in the OCI agent.
Writing Reports
Netflix-Skunkworks/oci-agent
Invoke this skill when writing oci-report.md from an executed OCI analysis.
Writing Specs
Netflix-Skunkworks/oci-agent
Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e.
Questions about Suggesting Remedies
What does Suggesting Remedies do?
Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed. Suggesting Remedies is an agent skill from Netflix-Skunkworks/oci-agent. Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed.
How do I install Suggesting Remedies in Claude Code?
Run `npx skills add Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a claude-code`. Or copy the skill folder (skills/suggesting-remedies in Netflix-Skunkworks/oci-agent) into .claude/skills/suggesting-remedies in your project. Claude Code loads it when a task matches its description.
How do I install Suggesting Remedies in Codex?
Run `npx skills add Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a codex`. Or copy the skill folder (skills/suggesting-remedies in Netflix-Skunkworks/oci-agent) into .agents/skills/suggesting-remedies in your project. Codex loads it when a task matches its description.
Can I use Suggesting Remedies 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 Netflix-Skunkworks/oci-agent --skill suggesting-remedies -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/suggesting-remedies, .gemini/skills/suggesting-remedies, .github/skills/suggesting-remedies and .opencode/skills/suggesting-remedies in your project.
What does Suggesting Remedies need to run?
SKILL.md names no scripts, command-line tools or credentials: Suggesting Remedies is instructions for the agent only.
Does Suggesting Remedies 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 Suggesting Remedies 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 Suggesting Remedies use?
Suggesting Remedies is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Suggesting Remedies use?
About 916 tokens (SKILL.md is roughly 3.7k 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 Suggesting Remedies?
Skills that share tags, products or a category with Suggesting Remedies: Suggestion Box (paperclipai/paperclip, 100k stars), Network Bgp Diagnostics (affaan-m/ECC, 277k stars), Triage Snmp Diagnostics (netdata/netdata, 81k stars) and Adding Ty Diagnostics (astral-sh/ruff, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Suggesting Remedies?
Netflix-Skunkworks (a GitHub organization) maintains it in Netflix-Skunkworks/oci-agent, which has 144 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 15, 2026.
Source: Netflix-Skunkworks/oci-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.